{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "---\n", "\n", "_You are currently looking at **version 1.3** of this notebook. To download notebooks and datafiles, as well as get help on Jupyter notebooks in the Coursera platform, visit the [Jupyter Notebook FAQ](https://www.coursera.org/learn/python-machine-learning/resources/bANLa) course resource._\n", "\n", "---" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Assignment 1 - Introduction to Machine Learning" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "For this assignment, you will be using the Breast Cancer Wisconsin (Diagnostic) Database to create a classifier that can help diagnose patients. First, read through the description of the dataset (below)." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Breast Cancer Wisconsin (Diagnostic) Database\n", "=============================================\n", "\n", "Notes\n", "-----\n", "Data Set Characteristics:\n", " :Number of Instances: 569\n", "\n", " :Number of Attributes: 30 numeric, predictive attributes and the class\n", "\n", " :Attribute Information:\n", " - radius (mean of distances from center to points on the perimeter)\n", " - texture (standard deviation of gray-scale values)\n", " - perimeter\n", " - area\n", " - smoothness (local variation in radius lengths)\n", " - compactness (perimeter^2 / area - 1.0)\n", " - concavity (severity of concave portions of the contour)\n", " - concave points (number of concave portions of the contour)\n", " - symmetry \n", " - fractal dimension (\"coastline approximation\" - 1)\n", "\n", " The mean, standard error, and \"worst\" or largest (mean of the three\n", " largest values) of these features were computed for each image,\n", " resulting in 30 features. For instance, field 3 is Mean Radius, field\n", " 13 is Radius SE, field 23 is Worst Radius.\n", "\n", " - class:\n", " - WDBC-Malignant\n", " - WDBC-Benign\n", "\n", " :Summary Statistics:\n", "\n", " ===================================== ====== ======\n", " Min Max\n", " ===================================== ====== ======\n", " radius (mean): 6.981 28.11\n", " texture (mean): 9.71 39.28\n", " perimeter (mean): 43.79 188.5\n", " area (mean): 143.5 2501.0\n", " smoothness (mean): 0.053 0.163\n", " compactness (mean): 0.019 0.345\n", " concavity (mean): 0.0 0.427\n", " concave points (mean): 0.0 0.201\n", " symmetry (mean): 0.106 0.304\n", " fractal dimension (mean): 0.05 0.097\n", " radius (standard error): 0.112 2.873\n", " texture (standard error): 0.36 4.885\n", " perimeter (standard error): 0.757 21.98\n", " area (standard error): 6.802 542.2\n", " smoothness (standard error): 0.002 0.031\n", " compactness (standard error): 0.002 0.135\n", " concavity (standard error): 0.0 0.396\n", " concave points (standard error): 0.0 0.053\n", " symmetry (standard error): 0.008 0.079\n", " fractal dimension (standard error): 0.001 0.03\n", " radius (worst): 7.93 36.04\n", " texture (worst): 12.02 49.54\n", " perimeter (worst): 50.41 251.2\n", " area (worst): 185.2 4254.0\n", " smoothness (worst): 0.071 0.223\n", " compactness (worst): 0.027 1.058\n", " concavity (worst): 0.0 1.252\n", " concave points (worst): 0.0 0.291\n", " symmetry (worst): 0.156 0.664\n", " fractal dimension (worst): 0.055 0.208\n", " ===================================== ====== ======\n", "\n", " :Missing Attribute Values: None\n", "\n", " :Class Distribution: 212 - Malignant, 357 - Benign\n", "\n", " :Creator: Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n", "\n", " :Donor: Nick Street\n", "\n", " :Date: November, 1995\n", "\n", "This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\n", "https://goo.gl/U2Uwz2\n", "\n", "Features are computed from a digitized image of a fine needle\n", "aspirate (FNA) of a breast mass. They describe\n", "characteristics of the cell nuclei present in the image.\n", "\n", "Separating plane described above was obtained using\n", "Multisurface Method-Tree (MSM-T) [K. P. Bennett, \"Decision Tree\n", "Construction Via Linear Programming.\" Proceedings of the 4th\n", "Midwest Artificial Intelligence and Cognitive Science Society,\n", "pp. 97-101, 1992], a classification method which uses linear\n", "programming to construct a decision tree. Relevant features\n", "were selected using an exhaustive search in the space of 1-4\n", "features and 1-3 separating planes.\n", "\n", "The actual linear program used to obtain the separating plane\n", "in the 3-dimensional space is that described in:\n", "[K. P. Bennett and O. L. Mangasarian: \"Robust Linear\n", "Programming Discrimination of Two Linearly Inseparable Sets\",\n", "Optimization Methods and Software 1, 1992, 23-34].\n", "\n", "This database is also available through the UW CS ftp server:\n", "\n", "ftp ftp.cs.wisc.edu\n", "cd math-prog/cpo-dataset/machine-learn/WDBC/\n", "\n", "References\n", "----------\n", " - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n", " for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n", " Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n", " San Jose, CA, 1993.\n", " - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n", " prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n", " July-August 1995.\n", " - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n", " to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n", " 163-171.\n", "\n" ] } ], "source": [ "import numpy as np\n", "import pandas as pd\n", "from sklearn.datasets import load_breast_cancer\n", "\n", "cancer = load_breast_cancer()\n", "\n", "print(cancer.DESCR) # Print the data set description" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The object returned by `load_breast_cancer()` is a scikit-learn Bunch object, which is similar to a dictionary." ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names'])" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "cancer.keys()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# data : Bunch\n", "# Dictionary-like object, the interesting attributes are:\n", "# ‘data’, the data to learn,\n", "# ‘target’, the classification labels, \n", "# ‘target_names’, the meaning of the labels, \n", "# ‘feature_names’, the meaning of the features, \n", "# ‘DESCR’, the full description of the dataset, \n", "# ‘filename’, the physical location of iris csv dataset " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 0 (Example)\n", "\n", "How many features does the breast cancer dataset have?\n", "\n", "*This function should return an integer.*" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "30" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# You should write your whole answer within the function provided. The autograder will call\n", "# this function and compare the return value against the correct solution value\n", "def answer_zero():\n", " # This function returns the number of features of the breast cancer dataset, which is an integer. \n", " # The assignment question description will tell you the general format the autograder is expecting\n", " return len(cancer['feature_names'])\n", "\n", "# You can examine what your function returns by calling it in the cell. If you have questions\n", "# about the assignment formats, check out the discussion forums for any FAQs\n", "answer_zero() " ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 1\n", "\n", "Scikit-learn works with lists, numpy arrays, scipy-sparse matrices, and pandas DataFrames, so converting the dataset to a DataFrame is not necessary for training this model. Using a DataFrame does however help make many things easier such as munging data, so let's practice creating a classifier with a pandas DataFrame. \n", "\n", "\n", "\n", "Convert the sklearn.dataset `cancer` to a DataFrame. \n", "\n", "*This function should return a `(569, 31)` DataFrame with * \n", "\n", "*columns = *\n", "\n", " ['mean radius', 'mean texture', 'mean perimeter', 'mean area',\n", " 'mean smoothness', 'mean compactness', 'mean concavity',\n", " 'mean concave points', 'mean symmetry', 'mean fractal dimension',\n", " 'radius error', 'texture error', 'perimeter error', 'area error',\n", " 'smoothness error', 'compactness error', 'concavity error',\n", " 'concave points error', 'symmetry error', 'fractal dimension error',\n", " 'worst radius', 'worst texture', 'worst perimeter', 'worst area',\n", " 'worst smoothness', 'worst compactness', 'worst concavity',\n", " 'worst concave points', 'worst symmetry', 'worst fractal dimension',\n", " 'target']\n", "\n", "*and index = *\n", "\n", " RangeIndex(start=0, stop=569, step=1)" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
mean radiusmean texturemean perimetermean areamean smoothnessmean compactnessmean concavitymean concave pointsmean symmetrymean fractal dimension...worst textureworst perimeterworst areaworst smoothnessworst compactnessworst concavityworst concave pointsworst symmetryworst fractal dimensiontarget
017.99010.38122.801001.00.118400.277600.3001000.1471000.24190.07871...17.33184.602019.00.162200.665600.711900.265400.46010.118900
120.57017.77132.901326.00.084740.078640.0869000.0701700.18120.05667...23.41158.801956.00.123800.186600.241600.186000.27500.089020
219.69021.25130.001203.00.109600.159900.1974000.1279000.20690.05999...25.53152.501709.00.144400.424500.450400.243000.36130.087580
311.42020.3877.58386.10.142500.283900.2414000.1052000.25970.09744...26.5098.87567.70.209800.866300.686900.257500.66380.173000
420.29014.34135.101297.00.100300.132800.1980000.1043000.18090.05883...16.67152.201575.00.137400.205000.400000.162500.23640.076780
512.45015.7082.57477.10.127800.170000.1578000.0808900.20870.07613...23.75103.40741.60.179100.524900.535500.174100.39850.124400
618.25019.98119.601040.00.094630.109000.1127000.0740000.17940.05742...27.66153.201606.00.144200.257600.378400.193200.30630.083680
713.71020.8390.20577.90.118900.164500.0936600.0598500.21960.07451...28.14110.60897.00.165400.368200.267800.155600.31960.115100
813.00021.8287.50519.80.127300.193200.1859000.0935300.23500.07389...30.73106.20739.30.170300.540100.539000.206000.43780.107200
912.46024.0483.97475.90.118600.239600.2273000.0854300.20300.08243...40.6897.65711.40.185301.058001.105000.221000.43660.207500
1016.02023.24102.70797.80.082060.066690.0329900.0332300.15280.05697...33.88123.801150.00.118100.155100.145900.099750.29480.084520
1115.78017.89103.60781.00.097100.129200.0995400.0660600.18420.06082...27.28136.501299.00.139600.560900.396500.181000.37920.104800
1219.17024.80132.401123.00.097400.245800.2065000.1118000.23970.07800...29.94151.701332.00.103700.390300.363900.176700.31760.102300
1315.85023.95103.70782.70.084010.100200.0993800.0536400.18470.05338...27.66112.00876.50.113100.192400.232200.111900.28090.062870
1413.73022.6193.60578.30.113100.229300.2128000.0802500.20690.07682...32.01108.80697.70.165100.772500.694300.220800.35960.143100
1514.54027.5496.73658.80.113900.159500.1639000.0736400.23030.07077...37.13124.10943.20.167800.657700.702600.171200.42180.134100
1614.68020.1394.74684.50.098670.072000.0739500.0525900.15860.05922...30.88123.401138.00.146400.187100.291400.160900.30290.082160
1716.13020.68108.10798.80.117000.202200.1722000.1028000.21640.07356...31.48136.801315.00.178900.423300.478400.207300.37060.114200
1819.81022.15130.001260.00.098310.102700.1479000.0949800.15820.05395...30.88186.802398.00.151200.315000.537200.238800.27680.076150
1913.54014.3687.46566.30.097790.081290.0666400.0478100.18850.05766...19.2699.70711.20.144000.177300.239000.128800.29770.072591
2013.08015.7185.63520.00.107500.127000.0456800.0311000.19670.06811...20.4996.09630.50.131200.277600.189000.072830.31840.081831
219.50412.4460.34273.90.102400.064920.0295600.0207600.18150.06905...15.6665.13314.90.132400.114800.088670.062270.24500.077731
2215.34014.26102.50704.40.107300.213500.2077000.0975600.25210.07032...19.08125.10980.90.139000.595400.630500.239300.46670.099460
2321.16023.04137.201404.00.094280.102200.1097000.0863200.17690.05278...35.59188.002615.00.140100.260000.315500.200900.28220.075260
2416.65021.38110.00904.60.112100.145700.1525000.0917000.19950.06330...31.56177.002215.00.180500.357800.469500.209500.36130.095640
2517.14016.40116.00912.70.118600.227600.2229000.1401000.30400.07413...21.40152.401461.00.154500.394900.385300.255000.40660.105900
2614.58021.5397.41644.80.105400.186800.1425000.0878300.22520.06924...33.21122.40896.90.152500.664300.553900.270100.42640.127500
2718.61020.25122.101094.00.094400.106600.1490000.0773100.16970.05699...27.26139.901403.00.133800.211700.344600.149000.23410.074210
2815.30025.27102.40732.40.108200.169700.1683000.0875100.19260.06540...36.71149.301269.00.164100.611000.633500.202400.40270.098760
2917.57015.05115.00955.10.098470.115700.0987500.0795300.17390.06149...19.52134.901227.00.125500.281200.248900.145600.27560.079190
..................................................................
5397.69125.4448.34170.40.086680.119900.0925200.0136400.20370.07751...31.8954.49223.60.159600.306400.339300.050000.27900.106601
54011.54014.4474.65402.90.099840.112000.0673700.0259400.18180.06782...19.6878.78457.80.134500.211800.179700.069180.23290.081341
54114.47024.9995.81656.40.088370.123000.1009000.0389000.18720.06341...31.73113.50808.90.134000.420200.404000.120500.31870.102301
54214.74025.4294.70668.60.082750.072140.0410500.0302700.18400.05680...32.29107.40826.40.106000.137600.161100.109500.27220.069561
54313.21028.0684.88538.40.086710.068770.0298700.0327500.16280.05781...37.1792.48629.60.107200.138100.106200.079580.24730.064431
54413.87020.7089.77584.80.095780.101800.0368800.0236900.16200.06688...24.7599.17688.60.126400.203700.137700.068450.22490.084921
54513.62023.2387.19573.20.092460.067470.0297400.0244300.16640.05801...29.0997.58729.80.121600.151700.104900.071740.26420.069531
54610.32016.3565.31324.90.094340.049940.0101200.0054950.18850.06201...21.7771.12384.90.128500.088420.043840.023810.26810.073991
54710.26016.5865.85320.80.088770.080660.0435800.0243800.16690.06714...22.0471.08357.40.146100.224600.178300.083330.26910.094791
5489.68319.3461.05285.70.084910.050300.0233700.0096150.15800.06235...25.5969.10364.20.119900.095460.093500.038460.25520.079201
54910.82024.2168.89361.60.081920.066020.0154800.0081600.19760.06328...31.4583.90505.60.120400.163300.061940.032640.30590.076261
55010.86021.4868.51360.50.074310.042270.0000000.0000000.16610.05948...24.7774.08412.30.100100.073480.000000.000000.24580.065921
55111.13022.4471.49378.40.095660.081940.0482400.0225700.20300.06552...28.2677.80436.60.108700.178200.156400.064130.31690.080321
55212.77029.4381.35507.90.082760.042340.0199700.0149900.15390.05637...36.0088.10594.70.123400.106400.086530.064980.24070.064841
5539.33321.9459.01264.00.092400.056050.0399600.0128200.16920.06576...25.0562.86295.80.110300.082980.079930.025640.24350.073931
55412.88028.9282.50514.30.081230.058240.0619500.0234300.15660.05708...35.7488.84595.70.122700.162000.243900.064930.23720.072421
55510.29027.6165.67321.40.090300.076580.0599900.0273800.15930.06127...34.9169.57357.60.138400.171000.200000.091270.22260.082831
55610.16019.5964.73311.70.100300.075040.0050250.0111600.17910.06331...22.8867.88347.30.126500.120000.010050.022320.22620.067421
5579.42327.8859.26271.30.081230.049710.0000000.0000000.17420.06059...34.2466.50330.60.107300.071580.000000.000000.24750.069691
55814.59022.6896.39657.10.084730.133000.1029000.0373600.14540.06147...27.27105.90733.50.102600.317100.366200.110500.22580.080041
55911.51023.9374.52403.50.092610.102100.1112000.0410500.13880.06570...37.1682.28474.20.129800.251700.363000.096530.21120.087321
56014.05027.1591.38600.40.099290.112600.0446200.0430400.15370.06171...33.17100.20706.70.124100.226400.132600.104800.22500.083211
56111.20029.3770.67386.00.074490.035580.0000000.0000000.10600.05502...38.3075.19439.60.092670.054940.000000.000000.15660.059051
56215.22030.62103.40716.90.104800.208700.2550000.0942900.21280.07152...42.79128.70915.00.141700.791701.170000.235600.40890.140900
56320.92025.09143.001347.00.109900.223600.3174000.1474000.21490.06879...29.41179.101819.00.140700.418600.659900.254200.29290.098730
56421.56022.39142.001479.00.111000.115900.2439000.1389000.17260.05623...26.40166.102027.00.141000.211300.410700.221600.20600.071150
56520.13028.25131.201261.00.097800.103400.1440000.0979100.17520.05533...38.25155.001731.00.116600.192200.321500.162800.25720.066370
56616.60028.08108.30858.10.084550.102300.0925100.0530200.15900.05648...34.12126.701124.00.113900.309400.340300.141800.22180.078200
56720.60029.33140.101265.00.117800.277000.3514000.1520000.23970.07016...39.42184.601821.00.165000.868100.938700.265000.40870.124000
5687.76024.5447.92181.00.052630.043620.0000000.0000000.15870.05884...30.3759.16268.60.089960.064440.000000.000000.28710.070391
\n", "

569 rows × 31 columns

\n", "
" ], "text/plain": [ " mean radius mean texture mean perimeter mean area mean smoothness \\\n", "0 17.990 10.38 122.80 1001.0 0.11840 \n", "1 20.570 17.77 132.90 1326.0 0.08474 \n", "2 19.690 21.25 130.00 1203.0 0.10960 \n", "3 11.420 20.38 77.58 386.1 0.14250 \n", "4 20.290 14.34 135.10 1297.0 0.10030 \n", "5 12.450 15.70 82.57 477.1 0.12780 \n", "6 18.250 19.98 119.60 1040.0 0.09463 \n", "7 13.710 20.83 90.20 577.9 0.11890 \n", "8 13.000 21.82 87.50 519.8 0.12730 \n", "9 12.460 24.04 83.97 475.9 0.11860 \n", "10 16.020 23.24 102.70 797.8 0.08206 \n", "11 15.780 17.89 103.60 781.0 0.09710 \n", "12 19.170 24.80 132.40 1123.0 0.09740 \n", "13 15.850 23.95 103.70 782.7 0.08401 \n", "14 13.730 22.61 93.60 578.3 0.11310 \n", "15 14.540 27.54 96.73 658.8 0.11390 \n", "16 14.680 20.13 94.74 684.5 0.09867 \n", "17 16.130 20.68 108.10 798.8 0.11700 \n", "18 19.810 22.15 130.00 1260.0 0.09831 \n", "19 13.540 14.36 87.46 566.3 0.09779 \n", "20 13.080 15.71 85.63 520.0 0.10750 \n", "21 9.504 12.44 60.34 273.9 0.10240 \n", "22 15.340 14.26 102.50 704.4 0.10730 \n", "23 21.160 23.04 137.20 1404.0 0.09428 \n", "24 16.650 21.38 110.00 904.6 0.11210 \n", "25 17.140 16.40 116.00 912.7 0.11860 \n", "26 14.580 21.53 97.41 644.8 0.10540 \n", "27 18.610 20.25 122.10 1094.0 0.09440 \n", "28 15.300 25.27 102.40 732.4 0.10820 \n", "29 17.570 15.05 115.00 955.1 0.09847 \n", ".. ... ... ... ... ... \n", "539 7.691 25.44 48.34 170.4 0.08668 \n", "540 11.540 14.44 74.65 402.9 0.09984 \n", "541 14.470 24.99 95.81 656.4 0.08837 \n", "542 14.740 25.42 94.70 668.6 0.08275 \n", "543 13.210 28.06 84.88 538.4 0.08671 \n", "544 13.870 20.70 89.77 584.8 0.09578 \n", "545 13.620 23.23 87.19 573.2 0.09246 \n", "546 10.320 16.35 65.31 324.9 0.09434 \n", "547 10.260 16.58 65.85 320.8 0.08877 \n", "548 9.683 19.34 61.05 285.7 0.08491 \n", "549 10.820 24.21 68.89 361.6 0.08192 \n", "550 10.860 21.48 68.51 360.5 0.07431 \n", "551 11.130 22.44 71.49 378.4 0.09566 \n", "552 12.770 29.43 81.35 507.9 0.08276 \n", "553 9.333 21.94 59.01 264.0 0.09240 \n", "554 12.880 28.92 82.50 514.3 0.08123 \n", "555 10.290 27.61 65.67 321.4 0.09030 \n", "556 10.160 19.59 64.73 311.7 0.10030 \n", "557 9.423 27.88 59.26 271.3 0.08123 \n", "558 14.590 22.68 96.39 657.1 0.08473 \n", "559 11.510 23.93 74.52 403.5 0.09261 \n", "560 14.050 27.15 91.38 600.4 0.09929 \n", "561 11.200 29.37 70.67 386.0 0.07449 \n", "562 15.220 30.62 103.40 716.9 0.10480 \n", "563 20.920 25.09 143.00 1347.0 0.10990 \n", "564 21.560 22.39 142.00 1479.0 0.11100 \n", "565 20.130 28.25 131.20 1261.0 0.09780 \n", "566 16.600 28.08 108.30 858.1 0.08455 \n", "567 20.600 29.33 140.10 1265.0 0.11780 \n", "568 7.760 24.54 47.92 181.0 0.05263 \n", "\n", " mean compactness mean concavity mean concave points mean symmetry \\\n", "0 0.27760 0.300100 0.147100 0.2419 \n", "1 0.07864 0.086900 0.070170 0.1812 \n", "2 0.15990 0.197400 0.127900 0.2069 \n", "3 0.28390 0.241400 0.105200 0.2597 \n", "4 0.13280 0.198000 0.104300 0.1809 \n", "5 0.17000 0.157800 0.080890 0.2087 \n", "6 0.10900 0.112700 0.074000 0.1794 \n", "7 0.16450 0.093660 0.059850 0.2196 \n", "8 0.19320 0.185900 0.093530 0.2350 \n", "9 0.23960 0.227300 0.085430 0.2030 \n", "10 0.06669 0.032990 0.033230 0.1528 \n", "11 0.12920 0.099540 0.066060 0.1842 \n", "12 0.24580 0.206500 0.111800 0.2397 \n", "13 0.10020 0.099380 0.053640 0.1847 \n", "14 0.22930 0.212800 0.080250 0.2069 \n", "15 0.15950 0.163900 0.073640 0.2303 \n", "16 0.07200 0.073950 0.052590 0.1586 \n", "17 0.20220 0.172200 0.102800 0.2164 \n", "18 0.10270 0.147900 0.094980 0.1582 \n", "19 0.08129 0.066640 0.047810 0.1885 \n", "20 0.12700 0.045680 0.031100 0.1967 \n", "21 0.06492 0.029560 0.020760 0.1815 \n", "22 0.21350 0.207700 0.097560 0.2521 \n", "23 0.10220 0.109700 0.086320 0.1769 \n", "24 0.14570 0.152500 0.091700 0.1995 \n", "25 0.22760 0.222900 0.140100 0.3040 \n", "26 0.18680 0.142500 0.087830 0.2252 \n", "27 0.10660 0.149000 0.077310 0.1697 \n", "28 0.16970 0.168300 0.087510 0.1926 \n", "29 0.11570 0.098750 0.079530 0.1739 \n", ".. ... ... ... ... \n", "539 0.11990 0.092520 0.013640 0.2037 \n", "540 0.11200 0.067370 0.025940 0.1818 \n", "541 0.12300 0.100900 0.038900 0.1872 \n", "542 0.07214 0.041050 0.030270 0.1840 \n", "543 0.06877 0.029870 0.032750 0.1628 \n", "544 0.10180 0.036880 0.023690 0.1620 \n", "545 0.06747 0.029740 0.024430 0.1664 \n", "546 0.04994 0.010120 0.005495 0.1885 \n", "547 0.08066 0.043580 0.024380 0.1669 \n", "548 0.05030 0.023370 0.009615 0.1580 \n", "549 0.06602 0.015480 0.008160 0.1976 \n", "550 0.04227 0.000000 0.000000 0.1661 \n", "551 0.08194 0.048240 0.022570 0.2030 \n", "552 0.04234 0.019970 0.014990 0.1539 \n", "553 0.05605 0.039960 0.012820 0.1692 \n", "554 0.05824 0.061950 0.023430 0.1566 \n", "555 0.07658 0.059990 0.027380 0.1593 \n", "556 0.07504 0.005025 0.011160 0.1791 \n", "557 0.04971 0.000000 0.000000 0.1742 \n", "558 0.13300 0.102900 0.037360 0.1454 \n", "559 0.10210 0.111200 0.041050 0.1388 \n", "560 0.11260 0.044620 0.043040 0.1537 \n", "561 0.03558 0.000000 0.000000 0.1060 \n", "562 0.20870 0.255000 0.094290 0.2128 \n", "563 0.22360 0.317400 0.147400 0.2149 \n", "564 0.11590 0.243900 0.138900 0.1726 \n", "565 0.10340 0.144000 0.097910 0.1752 \n", "566 0.10230 0.092510 0.053020 0.1590 \n", "567 0.27700 0.351400 0.152000 0.2397 \n", "568 0.04362 0.000000 0.000000 0.1587 \n", "\n", " mean fractal dimension ... worst texture worst perimeter \\\n", "0 0.07871 ... 17.33 184.60 \n", "1 0.05667 ... 23.41 158.80 \n", "2 0.05999 ... 25.53 152.50 \n", "3 0.09744 ... 26.50 98.87 \n", "4 0.05883 ... 16.67 152.20 \n", "5 0.07613 ... 23.75 103.40 \n", "6 0.05742 ... 27.66 153.20 \n", "7 0.07451 ... 28.14 110.60 \n", "8 0.07389 ... 30.73 106.20 \n", "9 0.08243 ... 40.68 97.65 \n", "10 0.05697 ... 33.88 123.80 \n", "11 0.06082 ... 27.28 136.50 \n", "12 0.07800 ... 29.94 151.70 \n", "13 0.05338 ... 27.66 112.00 \n", "14 0.07682 ... 32.01 108.80 \n", "15 0.07077 ... 37.13 124.10 \n", "16 0.05922 ... 30.88 123.40 \n", "17 0.07356 ... 31.48 136.80 \n", "18 0.05395 ... 30.88 186.80 \n", "19 0.05766 ... 19.26 99.70 \n", "20 0.06811 ... 20.49 96.09 \n", "21 0.06905 ... 15.66 65.13 \n", "22 0.07032 ... 19.08 125.10 \n", "23 0.05278 ... 35.59 188.00 \n", "24 0.06330 ... 31.56 177.00 \n", "25 0.07413 ... 21.40 152.40 \n", "26 0.06924 ... 33.21 122.40 \n", "27 0.05699 ... 27.26 139.90 \n", "28 0.06540 ... 36.71 149.30 \n", "29 0.06149 ... 19.52 134.90 \n", ".. ... ... ... ... \n", "539 0.07751 ... 31.89 54.49 \n", "540 0.06782 ... 19.68 78.78 \n", "541 0.06341 ... 31.73 113.50 \n", "542 0.05680 ... 32.29 107.40 \n", "543 0.05781 ... 37.17 92.48 \n", "544 0.06688 ... 24.75 99.17 \n", "545 0.05801 ... 29.09 97.58 \n", "546 0.06201 ... 21.77 71.12 \n", "547 0.06714 ... 22.04 71.08 \n", "548 0.06235 ... 25.59 69.10 \n", "549 0.06328 ... 31.45 83.90 \n", "550 0.05948 ... 24.77 74.08 \n", "551 0.06552 ... 28.26 77.80 \n", "552 0.05637 ... 36.00 88.10 \n", "553 0.06576 ... 25.05 62.86 \n", "554 0.05708 ... 35.74 88.84 \n", "555 0.06127 ... 34.91 69.57 \n", "556 0.06331 ... 22.88 67.88 \n", "557 0.06059 ... 34.24 66.50 \n", "558 0.06147 ... 27.27 105.90 \n", "559 0.06570 ... 37.16 82.28 \n", "560 0.06171 ... 33.17 100.20 \n", "561 0.05502 ... 38.30 75.19 \n", "562 0.07152 ... 42.79 128.70 \n", "563 0.06879 ... 29.41 179.10 \n", "564 0.05623 ... 26.40 166.10 \n", "565 0.05533 ... 38.25 155.00 \n", "566 0.05648 ... 34.12 126.70 \n", "567 0.07016 ... 39.42 184.60 \n", "568 0.05884 ... 30.37 59.16 \n", "\n", " worst area worst smoothness worst compactness worst concavity \\\n", "0 2019.0 0.16220 0.66560 0.71190 \n", "1 1956.0 0.12380 0.18660 0.24160 \n", "2 1709.0 0.14440 0.42450 0.45040 \n", "3 567.7 0.20980 0.86630 0.68690 \n", "4 1575.0 0.13740 0.20500 0.40000 \n", "5 741.6 0.17910 0.52490 0.53550 \n", "6 1606.0 0.14420 0.25760 0.37840 \n", "7 897.0 0.16540 0.36820 0.26780 \n", "8 739.3 0.17030 0.54010 0.53900 \n", "9 711.4 0.18530 1.05800 1.10500 \n", "10 1150.0 0.11810 0.15510 0.14590 \n", "11 1299.0 0.13960 0.56090 0.39650 \n", "12 1332.0 0.10370 0.39030 0.36390 \n", "13 876.5 0.11310 0.19240 0.23220 \n", "14 697.7 0.16510 0.77250 0.69430 \n", "15 943.2 0.16780 0.65770 0.70260 \n", "16 1138.0 0.14640 0.18710 0.29140 \n", "17 1315.0 0.17890 0.42330 0.47840 \n", "18 2398.0 0.15120 0.31500 0.53720 \n", "19 711.2 0.14400 0.17730 0.23900 \n", "20 630.5 0.13120 0.27760 0.18900 \n", "21 314.9 0.13240 0.11480 0.08867 \n", "22 980.9 0.13900 0.59540 0.63050 \n", "23 2615.0 0.14010 0.26000 0.31550 \n", "24 2215.0 0.18050 0.35780 0.46950 \n", "25 1461.0 0.15450 0.39490 0.38530 \n", "26 896.9 0.15250 0.66430 0.55390 \n", "27 1403.0 0.13380 0.21170 0.34460 \n", "28 1269.0 0.16410 0.61100 0.63350 \n", "29 1227.0 0.12550 0.28120 0.24890 \n", ".. ... ... ... ... \n", "539 223.6 0.15960 0.30640 0.33930 \n", "540 457.8 0.13450 0.21180 0.17970 \n", "541 808.9 0.13400 0.42020 0.40400 \n", "542 826.4 0.10600 0.13760 0.16110 \n", "543 629.6 0.10720 0.13810 0.10620 \n", "544 688.6 0.12640 0.20370 0.13770 \n", "545 729.8 0.12160 0.15170 0.10490 \n", "546 384.9 0.12850 0.08842 0.04384 \n", "547 357.4 0.14610 0.22460 0.17830 \n", "548 364.2 0.11990 0.09546 0.09350 \n", "549 505.6 0.12040 0.16330 0.06194 \n", "550 412.3 0.10010 0.07348 0.00000 \n", "551 436.6 0.10870 0.17820 0.15640 \n", "552 594.7 0.12340 0.10640 0.08653 \n", "553 295.8 0.11030 0.08298 0.07993 \n", "554 595.7 0.12270 0.16200 0.24390 \n", "555 357.6 0.13840 0.17100 0.20000 \n", "556 347.3 0.12650 0.12000 0.01005 \n", "557 330.6 0.10730 0.07158 0.00000 \n", "558 733.5 0.10260 0.31710 0.36620 \n", "559 474.2 0.12980 0.25170 0.36300 \n", "560 706.7 0.12410 0.22640 0.13260 \n", "561 439.6 0.09267 0.05494 0.00000 \n", "562 915.0 0.14170 0.79170 1.17000 \n", "563 1819.0 0.14070 0.41860 0.65990 \n", "564 2027.0 0.14100 0.21130 0.41070 \n", "565 1731.0 0.11660 0.19220 0.32150 \n", "566 1124.0 0.11390 0.30940 0.34030 \n", "567 1821.0 0.16500 0.86810 0.93870 \n", "568 268.6 0.08996 0.06444 0.00000 \n", "\n", " worst concave points worst symmetry worst fractal dimension target \n", "0 0.26540 0.4601 0.11890 0 \n", "1 0.18600 0.2750 0.08902 0 \n", "2 0.24300 0.3613 0.08758 0 \n", "3 0.25750 0.6638 0.17300 0 \n", "4 0.16250 0.2364 0.07678 0 \n", "5 0.17410 0.3985 0.12440 0 \n", "6 0.19320 0.3063 0.08368 0 \n", "7 0.15560 0.3196 0.11510 0 \n", "8 0.20600 0.4378 0.10720 0 \n", "9 0.22100 0.4366 0.20750 0 \n", "10 0.09975 0.2948 0.08452 0 \n", "11 0.18100 0.3792 0.10480 0 \n", "12 0.17670 0.3176 0.10230 0 \n", "13 0.11190 0.2809 0.06287 0 \n", "14 0.22080 0.3596 0.14310 0 \n", "15 0.17120 0.4218 0.13410 0 \n", "16 0.16090 0.3029 0.08216 0 \n", "17 0.20730 0.3706 0.11420 0 \n", "18 0.23880 0.2768 0.07615 0 \n", "19 0.12880 0.2977 0.07259 1 \n", "20 0.07283 0.3184 0.08183 1 \n", "21 0.06227 0.2450 0.07773 1 \n", "22 0.23930 0.4667 0.09946 0 \n", "23 0.20090 0.2822 0.07526 0 \n", "24 0.20950 0.3613 0.09564 0 \n", "25 0.25500 0.4066 0.10590 0 \n", "26 0.27010 0.4264 0.12750 0 \n", "27 0.14900 0.2341 0.07421 0 \n", "28 0.20240 0.4027 0.09876 0 \n", "29 0.14560 0.2756 0.07919 0 \n", ".. ... ... ... ... \n", "539 0.05000 0.2790 0.10660 1 \n", "540 0.06918 0.2329 0.08134 1 \n", "541 0.12050 0.3187 0.10230 1 \n", "542 0.10950 0.2722 0.06956 1 \n", "543 0.07958 0.2473 0.06443 1 \n", "544 0.06845 0.2249 0.08492 1 \n", "545 0.07174 0.2642 0.06953 1 \n", "546 0.02381 0.2681 0.07399 1 \n", "547 0.08333 0.2691 0.09479 1 \n", "548 0.03846 0.2552 0.07920 1 \n", "549 0.03264 0.3059 0.07626 1 \n", "550 0.00000 0.2458 0.06592 1 \n", "551 0.06413 0.3169 0.08032 1 \n", "552 0.06498 0.2407 0.06484 1 \n", "553 0.02564 0.2435 0.07393 1 \n", "554 0.06493 0.2372 0.07242 1 \n", "555 0.09127 0.2226 0.08283 1 \n", "556 0.02232 0.2262 0.06742 1 \n", "557 0.00000 0.2475 0.06969 1 \n", "558 0.11050 0.2258 0.08004 1 \n", "559 0.09653 0.2112 0.08732 1 \n", "560 0.10480 0.2250 0.08321 1 \n", "561 0.00000 0.1566 0.05905 1 \n", "562 0.23560 0.4089 0.14090 0 \n", "563 0.25420 0.2929 0.09873 0 \n", "564 0.22160 0.2060 0.07115 0 \n", "565 0.16280 0.2572 0.06637 0 \n", "566 0.14180 0.2218 0.07820 0 \n", "567 0.26500 0.4087 0.12400 0 \n", "568 0.00000 0.2871 0.07039 1 \n", "\n", "[569 rows x 31 columns]" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def answer_one():\n", " \n", " cancerdf = pd.concat([pd.DataFrame(cancer.data), pd.DataFrame(cancer.target)], axis=1)\n", " cancerdf.columns = np.append(cancer.feature_names,'target')\n", " return cancerdf\n", "\n", "answer_one()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 2\n", "What is the class distribution? (i.e. how many instances of `malignant` (encoded 0) and how many `benign` (encoded 1)?)\n", "\n", "*This function should return a Series named `target` of length 2 with integer values and index =* `['malignant', 'benign']`" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "benign 357\n", "malignant 212\n", "Name: target, dtype: int64" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def answer_two():\n", " cancerdf = answer_one()\n", " \n", " # Counts frequency of unique values. Useful!\n", " target = cancerdf['target'].value_counts()\n", " target.index = ['benign','malignant']\n", "\n", " return target\n", "\n", "answer_two()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 3\n", "Split the DataFrame into `X` (the data) and `y` (the labels).\n", "\n", "*This function should return a tuple of length 2:* `(X, y)`*, where* \n", "* `X`*, a pandas DataFrame, has shape* `(569, 30)`\n", "* `y`*, a pandas Series, has shape* `(569,)`." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "scrolled": true }, "outputs": [ { "data": { "text/plain": [ "( mean radius mean texture mean perimeter mean area mean smoothness \\\n", " 0 17.990 10.38 122.80 1001.0 0.11840 \n", " 1 20.570 17.77 132.90 1326.0 0.08474 \n", " 2 19.690 21.25 130.00 1203.0 0.10960 \n", " 3 11.420 20.38 77.58 386.1 0.14250 \n", " 4 20.290 14.34 135.10 1297.0 0.10030 \n", " 5 12.450 15.70 82.57 477.1 0.12780 \n", " 6 18.250 19.98 119.60 1040.0 0.09463 \n", " 7 13.710 20.83 90.20 577.9 0.11890 \n", " 8 13.000 21.82 87.50 519.8 0.12730 \n", " 9 12.460 24.04 83.97 475.9 0.11860 \n", " 10 16.020 23.24 102.70 797.8 0.08206 \n", " 11 15.780 17.89 103.60 781.0 0.09710 \n", " 12 19.170 24.80 132.40 1123.0 0.09740 \n", " 13 15.850 23.95 103.70 782.7 0.08401 \n", " 14 13.730 22.61 93.60 578.3 0.11310 \n", " 15 14.540 27.54 96.73 658.8 0.11390 \n", " 16 14.680 20.13 94.74 684.5 0.09867 \n", " 17 16.130 20.68 108.10 798.8 0.11700 \n", " 18 19.810 22.15 130.00 1260.0 0.09831 \n", " 19 13.540 14.36 87.46 566.3 0.09779 \n", " 20 13.080 15.71 85.63 520.0 0.10750 \n", " 21 9.504 12.44 60.34 273.9 0.10240 \n", " 22 15.340 14.26 102.50 704.4 0.10730 \n", " 23 21.160 23.04 137.20 1404.0 0.09428 \n", " 24 16.650 21.38 110.00 904.6 0.11210 \n", " 25 17.140 16.40 116.00 912.7 0.11860 \n", " 26 14.580 21.53 97.41 644.8 0.10540 \n", " 27 18.610 20.25 122.10 1094.0 0.09440 \n", " 28 15.300 25.27 102.40 732.4 0.10820 \n", " 29 17.570 15.05 115.00 955.1 0.09847 \n", " .. ... ... ... ... ... \n", " 539 7.691 25.44 48.34 170.4 0.08668 \n", " 540 11.540 14.44 74.65 402.9 0.09984 \n", " 541 14.470 24.99 95.81 656.4 0.08837 \n", " 542 14.740 25.42 94.70 668.6 0.08275 \n", " 543 13.210 28.06 84.88 538.4 0.08671 \n", " 544 13.870 20.70 89.77 584.8 0.09578 \n", " 545 13.620 23.23 87.19 573.2 0.09246 \n", " 546 10.320 16.35 65.31 324.9 0.09434 \n", " 547 10.260 16.58 65.85 320.8 0.08877 \n", " 548 9.683 19.34 61.05 285.7 0.08491 \n", " 549 10.820 24.21 68.89 361.6 0.08192 \n", " 550 10.860 21.48 68.51 360.5 0.07431 \n", " 551 11.130 22.44 71.49 378.4 0.09566 \n", " 552 12.770 29.43 81.35 507.9 0.08276 \n", " 553 9.333 21.94 59.01 264.0 0.09240 \n", " 554 12.880 28.92 82.50 514.3 0.08123 \n", " 555 10.290 27.61 65.67 321.4 0.09030 \n", " 556 10.160 19.59 64.73 311.7 0.10030 \n", " 557 9.423 27.88 59.26 271.3 0.08123 \n", " 558 14.590 22.68 96.39 657.1 0.08473 \n", " 559 11.510 23.93 74.52 403.5 0.09261 \n", " 560 14.050 27.15 91.38 600.4 0.09929 \n", " 561 11.200 29.37 70.67 386.0 0.07449 \n", " 562 15.220 30.62 103.40 716.9 0.10480 \n", " 563 20.920 25.09 143.00 1347.0 0.10990 \n", " 564 21.560 22.39 142.00 1479.0 0.11100 \n", " 565 20.130 28.25 131.20 1261.0 0.09780 \n", " 566 16.600 28.08 108.30 858.1 0.08455 \n", " 567 20.600 29.33 140.10 1265.0 0.11780 \n", " 568 7.760 24.54 47.92 181.0 0.05263 \n", " \n", " mean compactness mean concavity mean concave points mean symmetry \\\n", " 0 0.27760 0.300100 0.147100 0.2419 \n", " 1 0.07864 0.086900 0.070170 0.1812 \n", " 2 0.15990 0.197400 0.127900 0.2069 \n", " 3 0.28390 0.241400 0.105200 0.2597 \n", " 4 0.13280 0.198000 0.104300 0.1809 \n", " 5 0.17000 0.157800 0.080890 0.2087 \n", " 6 0.10900 0.112700 0.074000 0.1794 \n", " 7 0.16450 0.093660 0.059850 0.2196 \n", " 8 0.19320 0.185900 0.093530 0.2350 \n", " 9 0.23960 0.227300 0.085430 0.2030 \n", " 10 0.06669 0.032990 0.033230 0.1528 \n", " 11 0.12920 0.099540 0.066060 0.1842 \n", " 12 0.24580 0.206500 0.111800 0.2397 \n", " 13 0.10020 0.099380 0.053640 0.1847 \n", " 14 0.22930 0.212800 0.080250 0.2069 \n", " 15 0.15950 0.163900 0.073640 0.2303 \n", " 16 0.07200 0.073950 0.052590 0.1586 \n", " 17 0.20220 0.172200 0.102800 0.2164 \n", " 18 0.10270 0.147900 0.094980 0.1582 \n", " 19 0.08129 0.066640 0.047810 0.1885 \n", " 20 0.12700 0.045680 0.031100 0.1967 \n", " 21 0.06492 0.029560 0.020760 0.1815 \n", " 22 0.21350 0.207700 0.097560 0.2521 \n", " 23 0.10220 0.109700 0.086320 0.1769 \n", " 24 0.14570 0.152500 0.091700 0.1995 \n", " 25 0.22760 0.222900 0.140100 0.3040 \n", " 26 0.18680 0.142500 0.087830 0.2252 \n", " 27 0.10660 0.149000 0.077310 0.1697 \n", " 28 0.16970 0.168300 0.087510 0.1926 \n", " 29 0.11570 0.098750 0.079530 0.1739 \n", " .. ... ... ... ... \n", " 539 0.11990 0.092520 0.013640 0.2037 \n", " 540 0.11200 0.067370 0.025940 0.1818 \n", " 541 0.12300 0.100900 0.038900 0.1872 \n", " 542 0.07214 0.041050 0.030270 0.1840 \n", " 543 0.06877 0.029870 0.032750 0.1628 \n", " 544 0.10180 0.036880 0.023690 0.1620 \n", " 545 0.06747 0.029740 0.024430 0.1664 \n", " 546 0.04994 0.010120 0.005495 0.1885 \n", " 547 0.08066 0.043580 0.024380 0.1669 \n", " 548 0.05030 0.023370 0.009615 0.1580 \n", " 549 0.06602 0.015480 0.008160 0.1976 \n", " 550 0.04227 0.000000 0.000000 0.1661 \n", " 551 0.08194 0.048240 0.022570 0.2030 \n", " 552 0.04234 0.019970 0.014990 0.1539 \n", " 553 0.05605 0.039960 0.012820 0.1692 \n", " 554 0.05824 0.061950 0.023430 0.1566 \n", " 555 0.07658 0.059990 0.027380 0.1593 \n", " 556 0.07504 0.005025 0.011160 0.1791 \n", " 557 0.04971 0.000000 0.000000 0.1742 \n", " 558 0.13300 0.102900 0.037360 0.1454 \n", " 559 0.10210 0.111200 0.041050 0.1388 \n", " 560 0.11260 0.044620 0.043040 0.1537 \n", " 561 0.03558 0.000000 0.000000 0.1060 \n", " 562 0.20870 0.255000 0.094290 0.2128 \n", " 563 0.22360 0.317400 0.147400 0.2149 \n", " 564 0.11590 0.243900 0.138900 0.1726 \n", " 565 0.10340 0.144000 0.097910 0.1752 \n", " 566 0.10230 0.092510 0.053020 0.1590 \n", " 567 0.27700 0.351400 0.152000 0.2397 \n", " 568 0.04362 0.000000 0.000000 0.1587 \n", " \n", " mean fractal dimension ... worst radius \\\n", " 0 0.07871 ... 25.380 \n", " 1 0.05667 ... 24.990 \n", " 2 0.05999 ... 23.570 \n", " 3 0.09744 ... 14.910 \n", " 4 0.05883 ... 22.540 \n", " 5 0.07613 ... 15.470 \n", " 6 0.05742 ... 22.880 \n", " 7 0.07451 ... 17.060 \n", " 8 0.07389 ... 15.490 \n", " 9 0.08243 ... 15.090 \n", " 10 0.05697 ... 19.190 \n", " 11 0.06082 ... 20.420 \n", " 12 0.07800 ... 20.960 \n", " 13 0.05338 ... 16.840 \n", " 14 0.07682 ... 15.030 \n", " 15 0.07077 ... 17.460 \n", " 16 0.05922 ... 19.070 \n", " 17 0.07356 ... 20.960 \n", " 18 0.05395 ... 27.320 \n", " 19 0.05766 ... 15.110 \n", " 20 0.06811 ... 14.500 \n", " 21 0.06905 ... 10.230 \n", " 22 0.07032 ... 18.070 \n", " 23 0.05278 ... 29.170 \n", " 24 0.06330 ... 26.460 \n", " 25 0.07413 ... 22.250 \n", " 26 0.06924 ... 17.620 \n", " 27 0.05699 ... 21.310 \n", " 28 0.06540 ... 20.270 \n", " 29 0.06149 ... 20.010 \n", " .. ... ... ... \n", " 539 0.07751 ... 8.678 \n", " 540 0.06782 ... 12.260 \n", " 541 0.06341 ... 16.220 \n", " 542 0.05680 ... 16.510 \n", " 543 0.05781 ... 14.370 \n", " 544 0.06688 ... 15.050 \n", " 545 0.05801 ... 15.350 \n", " 546 0.06201 ... 11.250 \n", " 547 0.06714 ... 10.830 \n", " 548 0.06235 ... 10.930 \n", " 549 0.06328 ... 13.030 \n", " 550 0.05948 ... 11.660 \n", " 551 0.06552 ... 12.020 \n", " 552 0.05637 ... 13.870 \n", " 553 0.06576 ... 9.845 \n", " 554 0.05708 ... 13.890 \n", " 555 0.06127 ... 10.840 \n", " 556 0.06331 ... 10.650 \n", " 557 0.06059 ... 10.490 \n", " 558 0.06147 ... 15.480 \n", " 559 0.06570 ... 12.480 \n", " 560 0.06171 ... 15.300 \n", " 561 0.05502 ... 11.920 \n", " 562 0.07152 ... 17.520 \n", " 563 0.06879 ... 24.290 \n", " 564 0.05623 ... 25.450 \n", " 565 0.05533 ... 23.690 \n", " 566 0.05648 ... 18.980 \n", " 567 0.07016 ... 25.740 \n", " 568 0.05884 ... 9.456 \n", " \n", " worst texture worst perimeter worst area worst smoothness \\\n", " 0 17.33 184.60 2019.0 0.16220 \n", " 1 23.41 158.80 1956.0 0.12380 \n", " 2 25.53 152.50 1709.0 0.14440 \n", " 3 26.50 98.87 567.7 0.20980 \n", " 4 16.67 152.20 1575.0 0.13740 \n", " 5 23.75 103.40 741.6 0.17910 \n", " 6 27.66 153.20 1606.0 0.14420 \n", " 7 28.14 110.60 897.0 0.16540 \n", " 8 30.73 106.20 739.3 0.17030 \n", " 9 40.68 97.65 711.4 0.18530 \n", " 10 33.88 123.80 1150.0 0.11810 \n", " 11 27.28 136.50 1299.0 0.13960 \n", " 12 29.94 151.70 1332.0 0.10370 \n", " 13 27.66 112.00 876.5 0.11310 \n", " 14 32.01 108.80 697.7 0.16510 \n", " 15 37.13 124.10 943.2 0.16780 \n", " 16 30.88 123.40 1138.0 0.14640 \n", " 17 31.48 136.80 1315.0 0.17890 \n", " 18 30.88 186.80 2398.0 0.15120 \n", " 19 19.26 99.70 711.2 0.14400 \n", " 20 20.49 96.09 630.5 0.13120 \n", " 21 15.66 65.13 314.9 0.13240 \n", " 22 19.08 125.10 980.9 0.13900 \n", " 23 35.59 188.00 2615.0 0.14010 \n", " 24 31.56 177.00 2215.0 0.18050 \n", " 25 21.40 152.40 1461.0 0.15450 \n", " 26 33.21 122.40 896.9 0.15250 \n", " 27 27.26 139.90 1403.0 0.13380 \n", " 28 36.71 149.30 1269.0 0.16410 \n", " 29 19.52 134.90 1227.0 0.12550 \n", " .. ... ... ... ... \n", " 539 31.89 54.49 223.6 0.15960 \n", " 540 19.68 78.78 457.8 0.13450 \n", " 541 31.73 113.50 808.9 0.13400 \n", " 542 32.29 107.40 826.4 0.10600 \n", " 543 37.17 92.48 629.6 0.10720 \n", " 544 24.75 99.17 688.6 0.12640 \n", " 545 29.09 97.58 729.8 0.12160 \n", " 546 21.77 71.12 384.9 0.12850 \n", " 547 22.04 71.08 357.4 0.14610 \n", " 548 25.59 69.10 364.2 0.11990 \n", " 549 31.45 83.90 505.6 0.12040 \n", " 550 24.77 74.08 412.3 0.10010 \n", " 551 28.26 77.80 436.6 0.10870 \n", " 552 36.00 88.10 594.7 0.12340 \n", " 553 25.05 62.86 295.8 0.11030 \n", " 554 35.74 88.84 595.7 0.12270 \n", " 555 34.91 69.57 357.6 0.13840 \n", " 556 22.88 67.88 347.3 0.12650 \n", " 557 34.24 66.50 330.6 0.10730 \n", " 558 27.27 105.90 733.5 0.10260 \n", " 559 37.16 82.28 474.2 0.12980 \n", " 560 33.17 100.20 706.7 0.12410 \n", " 561 38.30 75.19 439.6 0.09267 \n", " 562 42.79 128.70 915.0 0.14170 \n", " 563 29.41 179.10 1819.0 0.14070 \n", " 564 26.40 166.10 2027.0 0.14100 \n", " 565 38.25 155.00 1731.0 0.11660 \n", " 566 34.12 126.70 1124.0 0.11390 \n", " 567 39.42 184.60 1821.0 0.16500 \n", " 568 30.37 59.16 268.6 0.08996 \n", " \n", " worst compactness worst concavity worst concave points worst symmetry \\\n", " 0 0.66560 0.71190 0.26540 0.4601 \n", " 1 0.18660 0.24160 0.18600 0.2750 \n", " 2 0.42450 0.45040 0.24300 0.3613 \n", " 3 0.86630 0.68690 0.25750 0.6638 \n", " 4 0.20500 0.40000 0.16250 0.2364 \n", " 5 0.52490 0.53550 0.17410 0.3985 \n", " 6 0.25760 0.37840 0.19320 0.3063 \n", " 7 0.36820 0.26780 0.15560 0.3196 \n", " 8 0.54010 0.53900 0.20600 0.4378 \n", " 9 1.05800 1.10500 0.22100 0.4366 \n", " 10 0.15510 0.14590 0.09975 0.2948 \n", " 11 0.56090 0.39650 0.18100 0.3792 \n", " 12 0.39030 0.36390 0.17670 0.3176 \n", " 13 0.19240 0.23220 0.11190 0.2809 \n", " 14 0.77250 0.69430 0.22080 0.3596 \n", " 15 0.65770 0.70260 0.17120 0.4218 \n", " 16 0.18710 0.29140 0.16090 0.3029 \n", " 17 0.42330 0.47840 0.20730 0.3706 \n", " 18 0.31500 0.53720 0.23880 0.2768 \n", " 19 0.17730 0.23900 0.12880 0.2977 \n", " 20 0.27760 0.18900 0.07283 0.3184 \n", " 21 0.11480 0.08867 0.06227 0.2450 \n", " 22 0.59540 0.63050 0.23930 0.4667 \n", " 23 0.26000 0.31550 0.20090 0.2822 \n", " 24 0.35780 0.46950 0.20950 0.3613 \n", " 25 0.39490 0.38530 0.25500 0.4066 \n", " 26 0.66430 0.55390 0.27010 0.4264 \n", " 27 0.21170 0.34460 0.14900 0.2341 \n", " 28 0.61100 0.63350 0.20240 0.4027 \n", " 29 0.28120 0.24890 0.14560 0.2756 \n", " .. ... ... ... ... \n", " 539 0.30640 0.33930 0.05000 0.2790 \n", " 540 0.21180 0.17970 0.06918 0.2329 \n", " 541 0.42020 0.40400 0.12050 0.3187 \n", " 542 0.13760 0.16110 0.10950 0.2722 \n", " 543 0.13810 0.10620 0.07958 0.2473 \n", " 544 0.20370 0.13770 0.06845 0.2249 \n", " 545 0.15170 0.10490 0.07174 0.2642 \n", " 546 0.08842 0.04384 0.02381 0.2681 \n", " 547 0.22460 0.17830 0.08333 0.2691 \n", " 548 0.09546 0.09350 0.03846 0.2552 \n", " 549 0.16330 0.06194 0.03264 0.3059 \n", " 550 0.07348 0.00000 0.00000 0.2458 \n", " 551 0.17820 0.15640 0.06413 0.3169 \n", " 552 0.10640 0.08653 0.06498 0.2407 \n", " 553 0.08298 0.07993 0.02564 0.2435 \n", " 554 0.16200 0.24390 0.06493 0.2372 \n", " 555 0.17100 0.20000 0.09127 0.2226 \n", " 556 0.12000 0.01005 0.02232 0.2262 \n", " 557 0.07158 0.00000 0.00000 0.2475 \n", " 558 0.31710 0.36620 0.11050 0.2258 \n", " 559 0.25170 0.36300 0.09653 0.2112 \n", " 560 0.22640 0.13260 0.10480 0.2250 \n", " 561 0.05494 0.00000 0.00000 0.1566 \n", " 562 0.79170 1.17000 0.23560 0.4089 \n", " 563 0.41860 0.65990 0.25420 0.2929 \n", " 564 0.21130 0.41070 0.22160 0.2060 \n", " 565 0.19220 0.32150 0.16280 0.2572 \n", " 566 0.30940 0.34030 0.14180 0.2218 \n", " 567 0.86810 0.93870 0.26500 0.4087 \n", " 568 0.06444 0.00000 0.00000 0.2871 \n", " \n", " worst fractal dimension \n", " 0 0.11890 \n", " 1 0.08902 \n", " 2 0.08758 \n", " 3 0.17300 \n", " 4 0.07678 \n", " 5 0.12440 \n", " 6 0.08368 \n", " 7 0.11510 \n", " 8 0.10720 \n", " 9 0.20750 \n", " 10 0.08452 \n", " 11 0.10480 \n", " 12 0.10230 \n", " 13 0.06287 \n", " 14 0.14310 \n", " 15 0.13410 \n", " 16 0.08216 \n", " 17 0.11420 \n", " 18 0.07615 \n", " 19 0.07259 \n", " 20 0.08183 \n", " 21 0.07773 \n", " 22 0.09946 \n", " 23 0.07526 \n", " 24 0.09564 \n", " 25 0.10590 \n", " 26 0.12750 \n", " 27 0.07421 \n", " 28 0.09876 \n", " 29 0.07919 \n", " .. ... \n", " 539 0.10660 \n", " 540 0.08134 \n", " 541 0.10230 \n", " 542 0.06956 \n", " 543 0.06443 \n", " 544 0.08492 \n", " 545 0.06953 \n", " 546 0.07399 \n", " 547 0.09479 \n", " 548 0.07920 \n", " 549 0.07626 \n", " 550 0.06592 \n", " 551 0.08032 \n", " 552 0.06484 \n", " 553 0.07393 \n", " 554 0.07242 \n", " 555 0.08283 \n", " 556 0.06742 \n", " 557 0.06969 \n", " 558 0.08004 \n", " 559 0.08732 \n", " 560 0.08321 \n", " 561 0.05905 \n", " 562 0.14090 \n", " 563 0.09873 \n", " 564 0.07115 \n", " 565 0.06637 \n", " 566 0.07820 \n", " 567 0.12400 \n", " 568 0.07039 \n", " \n", " [569 rows x 30 columns], 0 0\n", " 1 0\n", " 2 0\n", " 3 0\n", " 4 0\n", " 5 0\n", " 6 0\n", " 7 0\n", " 8 0\n", " 9 0\n", " 10 0\n", " 11 0\n", " 12 0\n", " 13 0\n", " 14 0\n", " 15 0\n", " 16 0\n", " 17 0\n", " 18 0\n", " 19 1\n", " 20 1\n", " 21 1\n", " 22 0\n", " 23 0\n", " 24 0\n", " 25 0\n", " 26 0\n", " 27 0\n", " 28 0\n", " 29 0\n", " ..\n", " 539 1\n", " 540 1\n", " 541 1\n", " 542 1\n", " 543 1\n", " 544 1\n", " 545 1\n", " 546 1\n", " 547 1\n", " 548 1\n", " 549 1\n", " 550 1\n", " 551 1\n", " 552 1\n", " 553 1\n", " 554 1\n", " 555 1\n", " 556 1\n", " 557 1\n", " 558 1\n", " 559 1\n", " 560 1\n", " 561 1\n", " 562 0\n", " 563 0\n", " 564 0\n", " 565 0\n", " 566 0\n", " 567 0\n", " 568 1\n", " Name: target, dtype: int64)" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# The last column 'target' has the labels.\n", "# Can also use cancerdf.ix[:,:-1] to select all columns but the last one.\n", "# cancerdf.ix[:,-1] to select just the last column.\n", "\n", "def answer_three():\n", " cancerdf = answer_one()\n", " \n", " X = cancerdf.drop('target', axis=1) # All columns but the last one.\n", " y = cancerdf['target'] # Just the last column.\n", " \n", " return X, y\n", "\n", "answer_three()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 4\n", "Using `train_test_split`, split `X` and `y` into training and test sets `(X_train, X_test, y_train, and y_test)`.\n", "\n", "**Set the random number generator state to 0 using `random_state=0` to make sure your results match the autograder!**\n", "\n", "*This function should return a tuple of length 4:* `(X_train, X_test, y_train, y_test)`*, where* \n", "* `X_train` *has shape* `(426, 30)`\n", "* `X_test` *has shape* `(143, 30)`\n", "* `y_train` *has shape* `(426,)`\n", "* `y_test` *has shape* `(143,)`" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "( mean radius mean texture mean perimeter mean area mean smoothness \\\n", " 293 11.850 17.46 75.54 432.7 0.08372 \n", " 332 11.220 19.86 71.94 387.3 0.10540 \n", " 565 20.130 28.25 131.20 1261.0 0.09780 \n", " 278 13.590 17.84 86.24 572.3 0.07948 \n", " 489 16.690 20.20 107.10 857.6 0.07497 \n", " 346 12.060 18.90 76.66 445.3 0.08386 \n", " 357 13.870 16.21 88.52 593.7 0.08743 \n", " 355 12.560 19.07 81.92 485.8 0.08760 \n", " 112 14.260 19.65 97.83 629.9 0.07837 \n", " 68 9.029 17.33 58.79 250.5 0.10660 \n", " 526 13.460 18.75 87.44 551.1 0.10750 \n", " 206 9.876 17.27 62.92 295.4 0.10890 \n", " 65 14.780 23.94 97.40 668.3 0.11720 \n", " 437 14.040 15.98 89.78 611.2 0.08458 \n", " 126 13.610 24.69 87.76 572.6 0.09258 \n", " 429 12.720 17.67 80.98 501.3 0.07896 \n", " 392 15.490 19.97 102.40 744.7 0.11600 \n", " 343 19.680 21.68 129.90 1194.0 0.09797 \n", " 334 12.300 19.02 77.88 464.4 0.08313 \n", " 440 10.970 17.20 71.73 371.5 0.08915 \n", " 441 17.270 25.42 112.40 928.8 0.08331 \n", " 137 11.430 15.39 73.06 399.8 0.09639 \n", " 230 17.050 19.08 113.40 895.0 0.11410 \n", " 7 13.710 20.83 90.20 577.9 0.11890 \n", " 408 17.990 20.66 117.80 991.7 0.10360 \n", " 523 13.710 18.68 88.73 571.0 0.09916 \n", " 361 13.300 21.57 85.24 546.1 0.08582 \n", " 553 9.333 21.94 59.01 264.0 0.09240 \n", " 478 11.490 14.59 73.99 404.9 0.10460 \n", " 303 10.490 18.61 66.86 334.3 0.10680 \n", " .. ... ... ... ... ... \n", " 459 9.755 28.20 61.68 290.9 0.07984 \n", " 510 11.740 14.69 76.31 426.0 0.08099 \n", " 151 8.219 20.70 53.27 203.9 0.09405 \n", " 244 19.400 23.50 129.10 1155.0 0.10270 \n", " 543 13.210 28.06 84.88 538.4 0.08671 \n", " 544 13.870 20.70 89.77 584.8 0.09578 \n", " 265 20.730 31.12 135.70 1419.0 0.09469 \n", " 288 11.260 19.96 73.72 394.1 0.08020 \n", " 423 13.660 19.13 89.46 575.3 0.09057 \n", " 147 14.950 18.77 97.84 689.5 0.08138 \n", " 177 16.460 20.11 109.30 832.9 0.09831 \n", " 99 14.420 19.77 94.48 642.5 0.09752 \n", " 448 14.530 19.34 94.25 659.7 0.08388 \n", " 431 12.400 17.68 81.47 467.8 0.10540 \n", " 115 11.930 21.53 76.53 438.6 0.09768 \n", " 72 17.200 24.52 114.20 929.4 0.10710 \n", " 537 11.690 24.44 76.37 406.4 0.12360 \n", " 174 10.660 15.15 67.49 349.6 0.08792 \n", " 87 19.020 24.59 122.00 1076.0 0.09029 \n", " 551 11.130 22.44 71.49 378.4 0.09566 \n", " 486 14.640 16.85 94.21 666.0 0.08641 \n", " 314 8.597 18.60 54.09 221.2 0.10740 \n", " 396 13.510 18.89 88.10 558.1 0.10590 \n", " 472 14.920 14.93 96.45 686.9 0.08098 \n", " 70 18.940 21.31 123.60 1130.0 0.09009 \n", " 277 18.810 19.98 120.90 1102.0 0.08923 \n", " 9 12.460 24.04 83.97 475.9 0.11860 \n", " 359 9.436 18.32 59.82 278.6 0.10090 \n", " 192 9.720 18.22 60.73 288.1 0.06950 \n", " 559 11.510 23.93 74.52 403.5 0.09261 \n", " \n", " mean compactness mean concavity mean concave points mean symmetry \\\n", " 293 0.05642 0.026880 0.022800 0.1875 \n", " 332 0.06779 0.005006 0.007583 0.1940 \n", " 565 0.10340 0.144000 0.097910 0.1752 \n", " 278 0.04052 0.019970 0.012380 0.1573 \n", " 489 0.07112 0.036490 0.023070 0.1846 \n", " 346 0.05794 0.007510 0.008488 0.1555 \n", " 357 0.05492 0.015020 0.020880 0.1424 \n", " 355 0.10380 0.103000 0.043910 0.1533 \n", " 112 0.22330 0.300300 0.077980 0.1704 \n", " 68 0.14130 0.313000 0.043750 0.2111 \n", " 526 0.11380 0.042010 0.031520 0.1723 \n", " 206 0.07232 0.017560 0.019520 0.1934 \n", " 65 0.14790 0.126700 0.090290 0.1953 \n", " 437 0.05895 0.035340 0.029440 0.1714 \n", " 126 0.07862 0.052850 0.030850 0.1761 \n", " 429 0.04522 0.014020 0.018350 0.1459 \n", " 392 0.15620 0.189100 0.091130 0.1929 \n", " 343 0.13390 0.186300 0.110300 0.2082 \n", " 334 0.04202 0.007756 0.008535 0.1539 \n", " 440 0.11130 0.094570 0.036130 0.1489 \n", " 441 0.11090 0.120400 0.057360 0.1467 \n", " 137 0.06889 0.035030 0.028750 0.1734 \n", " 230 0.15720 0.191000 0.109000 0.2131 \n", " 7 0.16450 0.093660 0.059850 0.2196 \n", " 408 0.13040 0.120100 0.088240 0.1992 \n", " 523 0.10700 0.053850 0.037830 0.1714 \n", " 361 0.06373 0.033440 0.024240 0.1815 \n", " 553 0.05605 0.039960 0.012820 0.1692 \n", " 478 0.08228 0.053080 0.019690 0.1779 \n", " 303 0.06678 0.022970 0.017800 0.1482 \n", " .. ... ... ... ... \n", " 459 0.04626 0.015410 0.010430 0.1621 \n", " 510 0.09661 0.067260 0.026390 0.1499 \n", " 151 0.13050 0.132100 0.021680 0.2222 \n", " 244 0.15580 0.204900 0.088860 0.1978 \n", " 543 0.06877 0.029870 0.032750 0.1628 \n", " 544 0.10180 0.036880 0.023690 0.1620 \n", " 265 0.11430 0.136700 0.086460 0.1769 \n", " 288 0.11810 0.092740 0.055880 0.2595 \n", " 423 0.11470 0.096570 0.048120 0.1848 \n", " 147 0.11670 0.090500 0.035620 0.1744 \n", " 177 0.15560 0.179300 0.088660 0.1794 \n", " 99 0.11410 0.093880 0.058390 0.1879 \n", " 448 0.07800 0.088170 0.029250 0.1473 \n", " 431 0.13160 0.077410 0.027990 0.1811 \n", " 115 0.07849 0.033280 0.020080 0.1688 \n", " 72 0.18300 0.169200 0.079440 0.1927 \n", " 537 0.15520 0.045150 0.045310 0.2131 \n", " 174 0.04302 0.000000 0.000000 0.1928 \n", " 87 0.12060 0.146800 0.082710 0.1953 \n", " 551 0.08194 0.048240 0.022570 0.2030 \n", " 486 0.06698 0.051920 0.027910 0.1409 \n", " 314 0.05847 0.000000 0.000000 0.2163 \n", " 396 0.11470 0.085800 0.053810 0.1806 \n", " 472 0.08549 0.055390 0.032210 0.1687 \n", " 70 0.10290 0.108000 0.079510 0.1582 \n", " 277 0.05884 0.080200 0.058430 0.1550 \n", " 9 0.23960 0.227300 0.085430 0.2030 \n", " 359 0.05956 0.027100 0.014060 0.1506 \n", " 192 0.02344 0.000000 0.000000 0.1653 \n", " 559 0.10210 0.111200 0.041050 0.1388 \n", " \n", " mean fractal dimension ... worst radius \\\n", " 293 0.05715 ... 13.060 \n", " 332 0.06028 ... 11.980 \n", " 565 0.05533 ... 23.690 \n", " 278 0.05520 ... 15.500 \n", " 489 0.05325 ... 19.180 \n", " 346 0.06048 ... 13.640 \n", " 357 0.05883 ... 15.110 \n", " 355 0.06184 ... 13.370 \n", " 112 0.07769 ... 15.300 \n", " 68 0.08046 ... 10.310 \n", " 526 0.06317 ... 15.350 \n", " 206 0.06285 ... 10.420 \n", " 65 0.06654 ... 17.310 \n", " 437 0.05898 ... 15.660 \n", " 126 0.06130 ... 16.890 \n", " 429 0.05544 ... 13.820 \n", " 392 0.06744 ... 21.200 \n", " 343 0.05715 ... 22.750 \n", " 334 0.05945 ... 13.350 \n", " 440 0.06640 ... 12.360 \n", " 441 0.05407 ... 20.380 \n", " 137 0.05865 ... 12.320 \n", " 230 0.06325 ... 19.590 \n", " 7 0.07451 ... 17.060 \n", " 408 0.06069 ... 21.080 \n", " 523 0.06843 ... 15.110 \n", " 361 0.05696 ... 14.200 \n", " 553 0.06576 ... 9.845 \n", " 478 0.06574 ... 12.400 \n", " 303 0.06600 ... 11.060 \n", " .. ... ... ... \n", " 459 0.05952 ... 10.670 \n", " 510 0.06758 ... 12.450 \n", " 151 0.08261 ... 9.092 \n", " 244 0.06000 ... 21.650 \n", " 543 0.05781 ... 14.370 \n", " 544 0.06688 ... 15.050 \n", " 265 0.05674 ... 32.490 \n", " 288 0.06233 ... 11.860 \n", " 423 0.06181 ... 15.140 \n", " 147 0.06493 ... 16.250 \n", " 177 0.06323 ... 17.790 \n", " 99 0.06390 ... 16.330 \n", " 448 0.05746 ... 16.300 \n", " 431 0.07102 ... 12.880 \n", " 115 0.06194 ... 13.670 \n", " 72 0.06487 ... 23.320 \n", " 537 0.07405 ... 12.980 \n", " 174 0.05975 ... 11.540 \n", " 87 0.05629 ... 24.560 \n", " 551 0.06552 ... 12.020 \n", " 486 0.05355 ... 16.460 \n", " 314 0.07359 ... 8.952 \n", " 396 0.06079 ... 14.800 \n", " 472 0.05669 ... 17.180 \n", " 70 0.05461 ... 24.860 \n", " 277 0.04996 ... 19.960 \n", " 9 0.08243 ... 15.090 \n", " 359 0.06959 ... 12.020 \n", " 192 0.06447 ... 9.968 \n", " 559 0.06570 ... 12.480 \n", " \n", " worst texture worst perimeter worst area worst smoothness \\\n", " 293 25.75 84.35 517.8 0.13690 \n", " 332 25.78 76.91 436.1 0.14240 \n", " 565 38.25 155.00 1731.0 0.11660 \n", " 278 26.10 98.91 739.1 0.10500 \n", " 489 26.56 127.30 1084.0 0.10090 \n", " 346 27.06 86.54 562.6 0.12890 \n", " 357 25.58 96.74 694.4 0.11530 \n", " 355 22.43 89.02 547.4 0.10960 \n", " 112 23.73 107.00 709.0 0.08949 \n", " 68 22.65 65.50 324.7 0.14820 \n", " 526 25.16 101.90 719.8 0.16240 \n", " 206 23.22 67.08 331.6 0.14150 \n", " 65 33.39 114.60 925.1 0.16480 \n", " 437 21.58 101.20 750.0 0.11950 \n", " 126 35.64 113.20 848.7 0.14710 \n", " 429 20.96 88.87 586.8 0.10680 \n", " 392 29.41 142.10 1359.0 0.16810 \n", " 343 34.66 157.60 1540.0 0.12180 \n", " 334 28.46 84.53 544.3 0.12220 \n", " 440 26.87 90.14 476.4 0.13910 \n", " 441 35.46 132.80 1284.0 0.14360 \n", " 137 22.02 79.93 462.0 0.11900 \n", " 230 24.89 133.50 1189.0 0.17030 \n", " 7 28.14 110.60 897.0 0.16540 \n", " 408 25.41 138.10 1349.0 0.14820 \n", " 523 25.63 99.43 701.9 0.14250 \n", " 361 29.20 92.94 621.2 0.11400 \n", " 553 25.05 62.86 295.8 0.11030 \n", " 478 21.90 82.04 467.6 0.13520 \n", " 303 24.54 70.76 375.4 0.14130 \n", " .. ... ... ... ... \n", " 459 36.92 68.03 349.9 0.11100 \n", " 510 17.60 81.25 473.8 0.10730 \n", " 151 29.72 58.08 249.8 0.16300 \n", " 244 30.53 144.90 1417.0 0.14630 \n", " 543 37.17 92.48 629.6 0.10720 \n", " 544 24.75 99.17 688.6 0.12640 \n", " 265 47.16 214.00 3432.0 0.14010 \n", " 288 22.33 78.27 437.6 0.10280 \n", " 423 25.50 101.40 708.8 0.11470 \n", " 147 25.47 107.10 809.7 0.09970 \n", " 177 28.45 123.50 981.2 0.14150 \n", " 99 30.86 109.50 826.4 0.14310 \n", " 448 28.39 108.10 830.5 0.10890 \n", " 431 22.91 89.61 515.8 0.14500 \n", " 115 26.15 87.54 583.0 0.15000 \n", " 72 33.82 151.60 1681.0 0.15850 \n", " 537 32.19 86.12 487.7 0.17680 \n", " 174 19.20 73.20 408.3 0.10760 \n", " 87 30.41 152.90 1623.0 0.12490 \n", " 551 28.26 77.80 436.6 0.10870 \n", " 486 25.44 106.00 831.0 0.11420 \n", " 314 22.44 56.65 240.1 0.13470 \n", " 396 27.20 97.33 675.2 0.14280 \n", " 472 18.22 112.00 906.6 0.10650 \n", " 70 26.58 165.90 1866.0 0.11930 \n", " 277 24.30 129.00 1236.0 0.12430 \n", " 9 40.68 97.65 711.4 0.18530 \n", " 359 25.02 75.79 439.6 0.13330 \n", " 192 20.83 62.25 303.8 0.07117 \n", " 559 37.16 82.28 474.2 0.12980 \n", " \n", " worst compactness worst concavity worst concave points worst symmetry \\\n", " 293 0.17580 0.13160 0.09140 0.3101 \n", " 332 0.09669 0.01335 0.02022 0.3292 \n", " 565 0.19220 0.32150 0.16280 0.2572 \n", " 278 0.07622 0.10600 0.05185 0.2335 \n", " 489 0.29200 0.24770 0.08737 0.4677 \n", " 346 0.13520 0.04506 0.05093 0.2880 \n", " 357 0.10080 0.05285 0.05556 0.2362 \n", " 355 0.20020 0.23880 0.09265 0.2121 \n", " 112 0.41930 0.67830 0.15050 0.2398 \n", " 68 0.43650 1.25200 0.17500 0.4228 \n", " 526 0.31240 0.26540 0.14270 0.3518 \n", " 206 0.12470 0.06213 0.05588 0.2989 \n", " 65 0.34160 0.30240 0.16140 0.3321 \n", " 437 0.12520 0.11170 0.07453 0.2725 \n", " 126 0.28840 0.37960 0.13290 0.3470 \n", " 429 0.09605 0.03469 0.03612 0.2165 \n", " 392 0.39130 0.55530 0.21210 0.3187 \n", " 343 0.34580 0.47340 0.22550 0.4045 \n", " 334 0.09052 0.03619 0.03983 0.2554 \n", " 440 0.40820 0.47790 0.15550 0.2540 \n", " 441 0.41220 0.50360 0.17390 0.2500 \n", " 137 0.16480 0.13990 0.08476 0.2676 \n", " 230 0.39340 0.50180 0.25430 0.3109 \n", " 7 0.36820 0.26780 0.15560 0.3196 \n", " 408 0.37350 0.33010 0.19740 0.3060 \n", " 523 0.25660 0.19350 0.12840 0.2849 \n", " 361 0.16670 0.12120 0.05614 0.2637 \n", " 553 0.08298 0.07993 0.02564 0.2435 \n", " 478 0.20100 0.25960 0.07431 0.2941 \n", " 303 0.10440 0.08423 0.06528 0.2213 \n", " .. ... ... ... ... \n", " 459 0.11090 0.07190 0.04866 0.2321 \n", " 510 0.27930 0.26900 0.10560 0.2604 \n", " 151 0.43100 0.53810 0.07879 0.3322 \n", " 244 0.29680 0.34580 0.15640 0.2920 \n", " 543 0.13810 0.10620 0.07958 0.2473 \n", " 544 0.20370 0.13770 0.06845 0.2249 \n", " 265 0.26440 0.34420 0.16590 0.2868 \n", " 288 0.18430 0.15460 0.09314 0.2955 \n", " 423 0.31670 0.36600 0.14070 0.2744 \n", " 147 0.25210 0.25000 0.08405 0.2852 \n", " 177 0.46670 0.58620 0.20350 0.3054 \n", " 99 0.30260 0.31940 0.15650 0.2718 \n", " 448 0.26490 0.37790 0.09594 0.2471 \n", " 431 0.26290 0.24030 0.07370 0.2556 \n", " 115 0.23990 0.15030 0.07247 0.2438 \n", " 72 0.73940 0.65660 0.18990 0.3313 \n", " 537 0.32510 0.13950 0.13080 0.2803 \n", " 174 0.06791 0.00000 0.00000 0.2710 \n", " 87 0.32060 0.57550 0.19560 0.3956 \n", " 551 0.17820 0.15640 0.06413 0.3169 \n", " 486 0.20700 0.24370 0.07828 0.2455 \n", " 314 0.07767 0.00000 0.00000 0.3142 \n", " 396 0.25700 0.34380 0.14530 0.2666 \n", " 472 0.27910 0.31510 0.11470 0.2688 \n", " 70 0.23360 0.26870 0.17890 0.2551 \n", " 277 0.11600 0.22100 0.12940 0.2567 \n", " 9 1.05800 1.10500 0.22100 0.4366 \n", " 359 0.10490 0.11440 0.05052 0.2454 \n", " 192 0.02729 0.00000 0.00000 0.1909 \n", " 559 0.25170 0.36300 0.09653 0.2112 \n", " \n", " worst fractal dimension \n", " 293 0.07007 \n", " 332 0.06522 \n", " 565 0.06637 \n", " 278 0.06263 \n", " 489 0.07623 \n", " 346 0.08083 \n", " 357 0.07113 \n", " 355 0.07188 \n", " 112 0.10820 \n", " 68 0.11750 \n", " 526 0.08665 \n", " 206 0.07380 \n", " 65 0.08911 \n", " 437 0.07234 \n", " 126 0.07900 \n", " 429 0.06025 \n", " 392 0.10190 \n", " 343 0.07918 \n", " 334 0.07207 \n", " 440 0.09532 \n", " 441 0.07944 \n", " 137 0.06765 \n", " 230 0.09061 \n", " 7 0.11510 \n", " 408 0.08503 \n", " 523 0.09031 \n", " 361 0.06658 \n", " 553 0.07393 \n", " 478 0.09180 \n", " 303 0.07842 \n", " .. ... \n", " 459 0.07211 \n", " 510 0.09879 \n", " 151 0.14860 \n", " 244 0.07614 \n", " 543 0.06443 \n", " 544 0.08492 \n", " 265 0.08218 \n", " 288 0.07009 \n", " 423 0.08839 \n", " 147 0.09218 \n", " 177 0.09519 \n", " 99 0.09353 \n", " 448 0.07463 \n", " 431 0.09359 \n", " 115 0.08541 \n", " 72 0.13390 \n", " 537 0.09970 \n", " 174 0.06164 \n", " 87 0.09288 \n", " 551 0.08032 \n", " 486 0.06596 \n", " 314 0.08116 \n", " 396 0.07686 \n", " 472 0.08273 \n", " 70 0.06589 \n", " 277 0.05737 \n", " 9 0.20750 \n", " 359 0.08136 \n", " 192 0.06559 \n", " 559 0.08732 \n", " \n", " [426 rows x 30 columns],\n", " mean radius mean texture mean perimeter mean area mean smoothness \\\n", " 512 13.400 20.52 88.64 556.7 0.11060 \n", " 457 13.210 25.25 84.10 537.9 0.08791 \n", " 439 14.020 15.66 89.59 606.5 0.07966 \n", " 298 14.260 18.17 91.22 633.1 0.06576 \n", " 37 13.030 18.42 82.61 523.8 0.08983 \n", " 515 11.340 18.61 72.76 391.2 0.10490 \n", " 382 12.050 22.72 78.75 447.8 0.06935 \n", " 310 11.700 19.11 74.33 418.7 0.08814 \n", " 538 7.729 25.49 47.98 178.8 0.08098 \n", " 345 10.260 14.71 66.20 321.6 0.09882 \n", " 421 14.690 13.98 98.22 656.1 0.10310 \n", " 90 14.620 24.02 94.57 662.7 0.08974 \n", " 412 9.397 21.68 59.75 268.8 0.07969 \n", " 157 16.840 19.46 108.40 880.2 0.07445 \n", " 89 14.640 15.24 95.77 651.9 0.11320 \n", " 172 15.460 11.89 102.50 736.9 0.12570 \n", " 318 9.042 18.90 60.07 244.5 0.09968 \n", " 233 20.510 27.81 134.40 1319.0 0.09159 \n", " 389 19.550 23.21 128.90 1174.0 0.10100 \n", " 250 20.940 23.56 138.90 1364.0 0.10070 \n", " 31 11.840 18.70 77.93 440.6 0.11090 \n", " 283 16.240 18.77 108.80 805.1 0.10660 \n", " 482 13.470 14.06 87.32 546.3 0.10710 \n", " 211 11.840 18.94 75.51 428.0 0.08871 \n", " 372 21.370 15.10 141.30 1386.0 0.10010 \n", " 401 11.930 10.91 76.14 442.7 0.08872 \n", " 159 10.900 12.96 68.69 366.8 0.07515 \n", " 14 13.730 22.61 93.60 578.3 0.11310 \n", " 364 13.400 16.95 85.48 552.4 0.07937 \n", " 337 18.770 21.43 122.90 1092.0 0.09116 \n", " .. ... ... ... ... ... \n", " 500 15.040 16.74 98.73 689.4 0.09883 \n", " 338 10.050 17.53 64.41 310.8 0.10070 \n", " 427 10.800 21.98 68.79 359.9 0.08801 \n", " 406 16.140 14.86 104.30 800.0 0.09495 \n", " 96 12.180 17.84 77.79 451.1 0.10450 \n", " 490 12.250 22.44 78.18 466.5 0.08192 \n", " 384 13.280 13.72 85.79 541.8 0.08363 \n", " 281 11.740 14.02 74.24 427.3 0.07813 \n", " 325 12.670 17.30 81.25 489.9 0.10280 \n", " 190 14.220 23.12 94.37 609.9 0.10750 \n", " 380 11.270 12.96 73.16 386.3 0.12370 \n", " 366 20.200 26.83 133.70 1234.0 0.09905 \n", " 469 11.620 18.18 76.38 408.8 0.11750 \n", " 225 14.340 13.47 92.51 641.2 0.09906 \n", " 271 11.290 13.04 72.23 388.0 0.09834 \n", " 547 10.260 16.58 65.85 320.8 0.08877 \n", " 550 10.860 21.48 68.51 360.5 0.07431 \n", " 492 18.010 20.56 118.40 1007.0 0.10010 \n", " 185 10.080 15.11 63.76 317.5 0.09267 \n", " 306 13.200 15.82 84.07 537.3 0.08511 \n", " 208 13.110 22.54 87.02 529.4 0.10020 \n", " 242 11.300 18.19 73.93 389.4 0.09592 \n", " 313 11.540 10.72 73.73 409.1 0.08597 \n", " 542 14.740 25.42 94.70 668.6 0.08275 \n", " 514 15.050 19.07 97.26 701.9 0.09215 \n", " 236 23.210 26.97 153.50 1670.0 0.09509 \n", " 113 10.510 20.19 68.64 334.2 0.11220 \n", " 527 12.340 12.27 78.94 468.5 0.09003 \n", " 76 13.530 10.94 87.91 559.2 0.12910 \n", " 162 19.590 18.15 130.70 1214.0 0.11200 \n", " \n", " mean compactness mean concavity mean concave points mean symmetry \\\n", " 512 0.14690 0.144500 0.081720 0.2116 \n", " 457 0.05205 0.027720 0.020680 0.1619 \n", " 439 0.05581 0.020870 0.026520 0.1589 \n", " 298 0.05220 0.024750 0.013740 0.1635 \n", " 37 0.03766 0.025620 0.029230 0.1467 \n", " 515 0.08499 0.043020 0.025940 0.1927 \n", " 382 0.10730 0.079430 0.029780 0.1203 \n", " 310 0.05253 0.015830 0.011480 0.1936 \n", " 538 0.04878 0.000000 0.000000 0.1870 \n", " 345 0.09159 0.035810 0.020370 0.1633 \n", " 421 0.18360 0.145000 0.063000 0.2086 \n", " 90 0.08606 0.031020 0.029570 0.1685 \n", " 412 0.06053 0.037350 0.005128 0.1274 \n", " 157 0.07223 0.051500 0.027710 0.1844 \n", " 89 0.13390 0.099660 0.070640 0.2116 \n", " 172 0.15550 0.203200 0.109700 0.1966 \n", " 318 0.19720 0.197500 0.049080 0.2330 \n", " 233 0.10740 0.155400 0.083400 0.1448 \n", " 389 0.13180 0.185600 0.102100 0.1989 \n", " 250 0.16060 0.271200 0.131000 0.2205 \n", " 31 0.15160 0.121800 0.051820 0.2301 \n", " 283 0.18020 0.194800 0.090520 0.1876 \n", " 482 0.11550 0.057860 0.052660 0.1779 \n", " 211 0.06900 0.026690 0.013930 0.1533 \n", " 372 0.15150 0.193200 0.125500 0.1973 \n", " 401 0.05242 0.026060 0.017960 0.1601 \n", " 159 0.03718 0.003090 0.006588 0.1442 \n", " 14 0.22930 0.212800 0.080250 0.2069 \n", " 364 0.05696 0.021810 0.014730 0.1650 \n", " 337 0.14020 0.106000 0.060900 0.1953 \n", " .. ... ... ... ... \n", " 500 0.13640 0.077210 0.061420 0.1668 \n", " 338 0.07326 0.025110 0.017750 0.1890 \n", " 427 0.05743 0.036140 0.014040 0.2016 \n", " 406 0.08501 0.055000 0.045280 0.1735 \n", " 96 0.07057 0.024900 0.029410 0.1900 \n", " 490 0.05200 0.017140 0.012610 0.1544 \n", " 384 0.08575 0.050770 0.028640 0.1617 \n", " 281 0.04340 0.022450 0.027630 0.2101 \n", " 325 0.07664 0.031930 0.021070 0.1707 \n", " 190 0.24130 0.198100 0.066180 0.2384 \n", " 380 0.11110 0.079000 0.055500 0.2018 \n", " 366 0.16690 0.164100 0.126500 0.1875 \n", " 469 0.14830 0.102000 0.055640 0.1957 \n", " 225 0.07624 0.057240 0.046030 0.2075 \n", " 271 0.07608 0.032650 0.027550 0.1769 \n", " 547 0.08066 0.043580 0.024380 0.1669 \n", " 550 0.04227 0.000000 0.000000 0.1661 \n", " 492 0.12890 0.117000 0.077620 0.2116 \n", " 185 0.04695 0.001597 0.002404 0.1703 \n", " 306 0.05251 0.001461 0.003261 0.1632 \n", " 208 0.14830 0.087050 0.051020 0.1850 \n", " 242 0.13250 0.154800 0.028540 0.2054 \n", " 313 0.05969 0.013670 0.008907 0.1833 \n", " 542 0.07214 0.041050 0.030270 0.1840 \n", " 514 0.08597 0.074860 0.043350 0.1561 \n", " 236 0.16820 0.195000 0.123700 0.1909 \n", " 113 0.13030 0.064760 0.030680 0.1922 \n", " 527 0.06307 0.029580 0.026470 0.1689 \n", " 76 0.10470 0.068770 0.065560 0.2403 \n", " 162 0.16660 0.250800 0.128600 0.2027 \n", " \n", " mean fractal dimension ... worst radius \\\n", " 512 0.07325 ... 16.410 \n", " 457 0.05584 ... 14.350 \n", " 439 0.05586 ... 14.910 \n", " 298 0.05586 ... 16.220 \n", " 37 0.05863 ... 13.300 \n", " 515 0.06211 ... 12.470 \n", " 382 0.06659 ... 12.570 \n", " 310 0.06128 ... 12.610 \n", " 538 0.07285 ... 9.077 \n", " 345 0.07005 ... 10.880 \n", " 421 0.07406 ... 16.460 \n", " 90 0.05866 ... 16.110 \n", " 412 0.06724 ... 9.965 \n", " 157 0.05268 ... 18.220 \n", " 89 0.06346 ... 16.340 \n", " 172 0.07069 ... 18.790 \n", " 318 0.08743 ... 10.060 \n", " 233 0.05592 ... 24.470 \n", " 389 0.05884 ... 20.820 \n", " 250 0.05898 ... 25.580 \n", " 31 0.07799 ... 16.820 \n", " 283 0.06684 ... 18.550 \n", " 482 0.06639 ... 14.830 \n", " 211 0.06057 ... 13.300 \n", " 372 0.06183 ... 22.690 \n", " 401 0.05541 ... 13.800 \n", " 159 0.05743 ... 12.360 \n", " 14 0.07682 ... 15.030 \n", " 364 0.05701 ... 14.730 \n", " 337 0.06083 ... 24.540 \n", " .. ... ... ... \n", " 500 0.06869 ... 16.760 \n", " 338 0.06331 ... 11.160 \n", " 427 0.05977 ... 12.760 \n", " 406 0.05875 ... 17.710 \n", " 96 0.06635 ... 12.830 \n", " 490 0.05976 ... 14.170 \n", " 384 0.05594 ... 14.240 \n", " 281 0.06113 ... 13.310 \n", " 325 0.05984 ... 13.710 \n", " 190 0.07542 ... 15.740 \n", " 380 0.06914 ... 12.840 \n", " 366 0.06020 ... 24.190 \n", " 469 0.07255 ... 13.360 \n", " 225 0.05448 ... 16.770 \n", " 271 0.06270 ... 12.320 \n", " 547 0.06714 ... 10.830 \n", " 550 0.05948 ... 11.660 \n", " 492 0.06077 ... 21.530 \n", " 185 0.06048 ... 11.870 \n", " 306 0.05894 ... 14.410 \n", " 208 0.07310 ... 14.550 \n", " 242 0.07669 ... 12.580 \n", " 313 0.06100 ... 12.340 \n", " 542 0.05680 ... 16.510 \n", " 514 0.05915 ... 17.580 \n", " 236 0.06309 ... 31.010 \n", " 113 0.07782 ... 11.160 \n", " 527 0.05808 ... 13.610 \n", " 76 0.06641 ... 14.080 \n", " 162 0.06082 ... 26.730 \n", " \n", " worst texture worst perimeter worst area worst smoothness \\\n", " 512 29.66 113.30 844.4 0.15740 \n", " 457 34.23 91.29 632.9 0.12890 \n", " 439 19.31 96.53 688.9 0.10340 \n", " 298 25.26 105.80 819.7 0.09445 \n", " 37 22.81 84.46 545.9 0.09701 \n", " 515 23.03 79.15 478.6 0.14830 \n", " 382 28.71 87.36 488.4 0.08799 \n", " 310 26.55 80.92 483.1 0.12230 \n", " 538 30.92 57.17 248.0 0.12560 \n", " 345 19.48 70.89 357.1 0.13600 \n", " 421 18.34 114.10 809.2 0.13120 \n", " 90 29.11 102.90 803.7 0.11150 \n", " 412 27.99 66.61 301.0 0.10860 \n", " 157 28.07 120.30 1032.0 0.08774 \n", " 89 18.24 109.40 803.6 0.12770 \n", " 172 17.04 125.00 1102.0 0.15310 \n", " 318 23.40 68.62 297.1 0.12210 \n", " 233 37.38 162.70 1872.0 0.12230 \n", " 389 30.44 142.00 1313.0 0.12510 \n", " 250 27.00 165.30 2010.0 0.12110 \n", " 31 28.12 119.40 888.7 0.16370 \n", " 283 25.09 126.90 1031.0 0.13650 \n", " 482 18.32 94.94 660.2 0.13930 \n", " 211 24.99 85.22 546.3 0.12800 \n", " 372 21.84 152.10 1535.0 0.11920 \n", " 401 20.14 87.64 589.5 0.13740 \n", " 159 18.20 78.07 470.0 0.11710 \n", " 14 32.01 108.80 697.7 0.16510 \n", " 364 21.70 93.76 663.5 0.12130 \n", " 337 34.37 161.10 1873.0 0.14980 \n", " .. ... ... ... ... \n", " 500 20.43 109.70 856.9 0.11350 \n", " 338 26.84 71.98 384.0 0.14020 \n", " 427 32.04 83.69 489.5 0.13030 \n", " 406 19.58 115.90 947.9 0.12060 \n", " 96 20.92 82.14 495.2 0.11400 \n", " 490 31.99 92.74 622.9 0.12560 \n", " 384 17.37 96.59 623.7 0.11660 \n", " 281 18.26 84.70 533.7 0.10360 \n", " 325 21.10 88.70 574.4 0.13840 \n", " 190 37.18 106.40 762.4 0.15330 \n", " 380 20.53 84.93 476.1 0.16100 \n", " 366 33.81 160.00 1671.0 0.12780 \n", " 469 25.40 88.14 528.1 0.17800 \n", " 225 16.90 110.40 873.2 0.12970 \n", " 271 16.18 78.27 457.5 0.13580 \n", " 547 22.04 71.08 357.4 0.14610 \n", " 550 24.77 74.08 412.3 0.10010 \n", " 492 26.06 143.40 1426.0 0.13090 \n", " 185 21.18 75.39 437.0 0.15210 \n", " 306 20.45 92.00 636.9 0.11280 \n", " 208 29.16 99.48 639.3 0.13490 \n", " 242 27.96 87.16 472.9 0.13470 \n", " 313 12.87 81.23 467.8 0.10920 \n", " 542 32.29 107.40 826.4 0.10600 \n", " 514 28.06 113.80 967.0 0.12460 \n", " 236 34.51 206.00 2944.0 0.14810 \n", " 113 22.75 72.62 374.4 0.13000 \n", " 527 19.27 87.22 564.9 0.12920 \n", " 76 12.49 91.36 605.5 0.14510 \n", " 162 26.39 174.90 2232.0 0.14380 \n", " \n", " worst compactness worst concavity worst concave points worst symmetry \\\n", " 512 0.38560 0.51060 0.20510 0.3585 \n", " 457 0.10630 0.13900 0.06005 0.2444 \n", " 439 0.10170 0.06260 0.08216 0.2136 \n", " 298 0.21670 0.15650 0.07530 0.2636 \n", " 37 0.04619 0.04833 0.05013 0.1987 \n", " 515 0.15740 0.16240 0.08542 0.3060 \n", " 382 0.32140 0.29120 0.10920 0.2191 \n", " 310 0.10870 0.07915 0.05741 0.3487 \n", " 538 0.08340 0.00000 0.00000 0.3058 \n", " 345 0.16360 0.07162 0.04074 0.2434 \n", " 421 0.36350 0.32190 0.11080 0.2827 \n", " 90 0.17660 0.09189 0.06946 0.2522 \n", " 412 0.18870 0.18680 0.02564 0.2376 \n", " 157 0.17100 0.18820 0.08436 0.2527 \n", " 89 0.30890 0.26040 0.13970 0.3151 \n", " 172 0.35830 0.58300 0.18270 0.3216 \n", " 318 0.37480 0.46090 0.11450 0.3135 \n", " 233 0.27610 0.41460 0.15630 0.2437 \n", " 389 0.24140 0.38290 0.18250 0.2576 \n", " 250 0.31720 0.69910 0.21050 0.3126 \n", " 31 0.57750 0.69560 0.15460 0.4761 \n", " 283 0.47060 0.50260 0.17320 0.2770 \n", " 482 0.24990 0.18480 0.13350 0.3227 \n", " 211 0.18800 0.14710 0.06913 0.2535 \n", " 372 0.28400 0.40240 0.19660 0.2730 \n", " 401 0.15750 0.15140 0.06876 0.2460 \n", " 159 0.08294 0.01854 0.03953 0.2738 \n", " 14 0.77250 0.69430 0.22080 0.3596 \n", " 364 0.16760 0.13640 0.06987 0.2741 \n", " 337 0.48270 0.46340 0.20480 0.3679 \n", " .. ... ... ... ... \n", " 500 0.21760 0.18560 0.10180 0.2177 \n", " 338 0.14020 0.10550 0.06499 0.2894 \n", " 427 0.16960 0.19270 0.07485 0.2965 \n", " 406 0.17220 0.23100 0.11290 0.2778 \n", " 96 0.09358 0.04980 0.05882 0.2227 \n", " 490 0.18040 0.12300 0.06335 0.3100 \n", " 384 0.26850 0.28660 0.09173 0.2736 \n", " 281 0.08500 0.06735 0.08290 0.3101 \n", " 325 0.12120 0.10200 0.05602 0.2688 \n", " 190 0.93270 0.84880 0.17720 0.5166 \n", " 380 0.24290 0.22470 0.13180 0.3343 \n", " 366 0.34160 0.37030 0.21520 0.3271 \n", " 469 0.28780 0.31860 0.14160 0.2660 \n", " 225 0.15250 0.16320 0.10870 0.3062 \n", " 271 0.15070 0.12750 0.08750 0.2733 \n", " 547 0.22460 0.17830 0.08333 0.2691 \n", " 550 0.07348 0.00000 0.00000 0.2458 \n", " 492 0.23270 0.25440 0.14890 0.3251 \n", " 185 0.10190 0.00692 0.01042 0.2933 \n", " 306 0.13460 0.01120 0.02500 0.2651 \n", " 208 0.44020 0.31620 0.11260 0.4128 \n", " 242 0.48480 0.74360 0.12180 0.3308 \n", " 313 0.16260 0.08324 0.04715 0.3390 \n", " 542 0.13760 0.16110 0.10950 0.2722 \n", " 514 0.21010 0.28660 0.11200 0.2282 \n", " 236 0.41260 0.58200 0.25930 0.3103 \n", " 113 0.20490 0.12950 0.06136 0.2383 \n", " 527 0.20740 0.17910 0.10700 0.3110 \n", " 76 0.13790 0.08539 0.07407 0.2710 \n", " 162 0.38460 0.68100 0.22470 0.3643 \n", " \n", " worst fractal dimension \n", " 512 0.11090 \n", " 457 0.06788 \n", " 439 0.06710 \n", " 298 0.07676 \n", " 37 0.06169 \n", " 515 0.06783 \n", " 382 0.09349 \n", " 310 0.06958 \n", " 538 0.09938 \n", " 345 0.08488 \n", " 421 0.09208 \n", " 90 0.07246 \n", " 412 0.09206 \n", " 157 0.05972 \n", " 89 0.08473 \n", " 172 0.10100 \n", " 318 0.10550 \n", " 233 0.08328 \n", " 389 0.07602 \n", " 250 0.07849 \n", " 31 0.14020 \n", " 283 0.10630 \n", " 482 0.09326 \n", " 211 0.07993 \n", " 372 0.08666 \n", " 401 0.07262 \n", " 159 0.07685 \n", " 14 0.14310 \n", " 364 0.07582 \n", " 337 0.09870 \n", " .. ... \n", " 500 0.08549 \n", " 338 0.07664 \n", " 427 0.07662 \n", " 406 0.07012 \n", " 96 0.07376 \n", " 490 0.08203 \n", " 384 0.07320 \n", " 281 0.06688 \n", " 325 0.06888 \n", " 190 0.14460 \n", " 380 0.09215 \n", " 366 0.07632 \n", " 469 0.09270 \n", " 225 0.06072 \n", " 271 0.08022 \n", " 547 0.09479 \n", " 550 0.06592 \n", " 492 0.07625 \n", " 185 0.07697 \n", " 306 0.08385 \n", " 208 0.10760 \n", " 242 0.12970 \n", " 313 0.07434 \n", " 542 0.06956 \n", " 514 0.06954 \n", " 236 0.08677 \n", " 113 0.09026 \n", " 527 0.07592 \n", " 76 0.07191 \n", " 162 0.09223 \n", " \n", " [143 rows x 30 columns],\n", " 293 1\n", " 332 1\n", " 565 0\n", " 278 1\n", " 489 0\n", " 346 1\n", " 357 1\n", " 355 1\n", " 112 1\n", " 68 1\n", " 526 1\n", " 206 1\n", " 65 0\n", " 437 1\n", " 126 0\n", " 429 1\n", " 392 0\n", " 343 0\n", " 334 1\n", " 440 1\n", " 441 0\n", " 137 1\n", " 230 0\n", " 7 0\n", " 408 0\n", " 523 1\n", " 361 1\n", " 553 1\n", " 478 1\n", " 303 1\n", " ..\n", " 459 1\n", " 510 1\n", " 151 1\n", " 244 0\n", " 543 1\n", " 544 1\n", " 265 0\n", " 288 1\n", " 423 1\n", " 147 1\n", " 177 0\n", " 99 0\n", " 448 1\n", " 431 1\n", " 115 1\n", " 72 0\n", " 537 1\n", " 174 1\n", " 87 0\n", " 551 1\n", " 486 1\n", " 314 1\n", " 396 1\n", " 472 1\n", " 70 0\n", " 277 0\n", " 9 0\n", " 359 1\n", " 192 1\n", " 559 1\n", " Name: target, dtype: int64,\n", " 512 0\n", " 457 1\n", " 439 1\n", " 298 1\n", " 37 1\n", " 515 1\n", " 382 1\n", " 310 1\n", " 538 1\n", " 345 1\n", " 421 1\n", " 90 1\n", " 412 1\n", " 157 1\n", " 89 1\n", " 172 0\n", " 318 1\n", " 233 0\n", " 389 0\n", " 250 0\n", " 31 0\n", " 283 0\n", " 482 1\n", " 211 1\n", " 372 0\n", " 401 1\n", " 159 1\n", " 14 0\n", " 364 1\n", " 337 0\n", " ..\n", " 500 1\n", " 338 1\n", " 427 1\n", " 406 1\n", " 96 1\n", " 490 1\n", " 384 1\n", " 281 1\n", " 325 1\n", " 190 0\n", " 380 1\n", " 366 0\n", " 469 1\n", " 225 1\n", " 271 1\n", " 547 1\n", " 550 1\n", " 492 0\n", " 185 1\n", " 306 1\n", " 208 1\n", " 242 1\n", " 313 1\n", " 542 1\n", " 514 0\n", " 236 0\n", " 113 1\n", " 527 1\n", " 76 1\n", " 162 0\n", " Name: target, dtype: int64)" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "def answer_four():\n", " X, y = answer_three()\n", " \n", " X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n", " \n", " return X_train, X_test, y_train, y_test\n", "\n", "answer_four()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 5\n", "Using KNeighborsClassifier, fit a k-nearest neighbors (knn) classifier with `X_train`, `y_train` and using one nearest neighbor (`n_neighbors = 1`).\n", "\n", "*This function should return a * `sklearn.neighbors.classification.KNeighborsClassifier`." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n", " metric_params=None, n_jobs=1, n_neighbors=1, p=2,\n", " weights='uniform')" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.neighbors import KNeighborsClassifier\n", "\n", "def answer_five():\n", " X_train, X_test, y_train, y_test = answer_four()\n", " \n", " knn = KNeighborsClassifier(n_neighbors = 1)\n", " knn.fit(X_train, y_train)\n", " \n", " return knn\n", "\n", "answer_five()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 6\n", "Using your knn classifier, predict the class label using the mean value for each feature.\n", "\n", "Hint: You can use `cancerdf.mean()[:-1].values.reshape(1, -1)` which gets the mean value for each feature, ignores the target column, and reshapes the data from 1 dimension to 2 (necessary for the precict method of KNeighborsClassifier).\n", "\n", "*This function should return a numpy array either `array([ 0.])` or `array([ 1.])`*" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1])" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def answer_six():\n", " cancerdf = answer_one()\n", " knn = answer_five()\n", " # Remember a dimension is added to whichever position has 1 in reshape.\n", " # If you have reshape(1,-1) a dimension is added to the rows, i.e, the shape goes from being '30,' to '1,30'.\n", " # If you do reshape(-1,1) a dimension is added the columns.\n", " means = cancerdf.mean()[:-1].values.reshape(1, -1)\n", " #return means.shape\n", " \n", " pred = knn.predict(means)\n", " return pred\n", " \n", "answer_six()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 7\n", "Using your knn classifier, predict the class labels for the test set `X_test`.\n", "\n", "*This function should return a numpy array with shape `(143,)` and values either `0.0` or `1.0`.*" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1,\n", " 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0,\n", " 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0,\n", " 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 1, 0,\n", " 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1,\n", " 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0,\n", " 0, 1, 1, 1, 0])" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def answer_seven():\n", " X_train, X_test, y_train, y_test = answer_four()\n", " knn = answer_five()\n", " \n", " pred1 = knn.predict(X_test)\n", " return pred1\n", "\n", "answer_seven()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Question 8\n", "Find the score (mean accuracy) of your knn classifier using `X_test` and `y_test`.\n", "\n", "*This function should return a float between 0 and 1*" ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0.91608391608391604" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "def answer_eight():\n", " X_train, X_test, y_train, y_test = answer_four()\n", " knn = answer_five()\n", " \n", " return knn.score(X_test, y_test)\n", "\n", "answer_eight()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Optional plot\n", "\n", "Try using the plotting function below to visualize the differet predicition scores between training and test sets, as well as malignant and benign cells." ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def accuracy_plot():\n", " import matplotlib.pyplot as plt\n", "\n", " %matplotlib notebook\n", "\n", " X_train, X_test, y_train, y_test = answer_four()\n", "\n", " # Find the training and testing accuracies by target value (i.e. malignant, benign)\n", " mal_train_X = X_train[y_train==0]\n", " mal_train_y = y_train[y_train==0]\n", " ben_train_X = X_train[y_train==1]\n", " ben_train_y = y_train[y_train==1]\n", "\n", " mal_test_X = X_test[y_test==0]\n", " mal_test_y = y_test[y_test==0]\n", " ben_test_X = X_test[y_test==1]\n", " ben_test_y = y_test[y_test==1]\n", "\n", " knn = answer_five()\n", "\n", " scores = [knn.score(mal_train_X, mal_train_y), knn.score(ben_train_X, ben_train_y), \n", " knn.score(mal_test_X, mal_test_y), knn.score(ben_test_X, ben_test_y)]\n", "\n", "\n", " plt.figure()\n", "\n", " # Plot the scores as a bar chart\n", " bars = plt.bar(np.arange(4), scores, color=['#4c72b0','#4c72b0','#55a868','#55a868'])\n", "\n", " # directly label the score onto the bars\n", " for bar in bars:\n", " height = bar.get_height()\n", " plt.gca().text(bar.get_x() + bar.get_width()/2, height*.90, '{0:.{1}f}'.format(height, 2), \n", " ha='center', color='w', fontsize=11)\n", "\n", " # remove all the ticks (both axes), and tick labels on the Y axis\n", " plt.tick_params(top='off', bottom='off', left='off', right='off', labelleft='off', labelbottom='on')\n", "\n", " # remove the frame of the chart\n", " for spine in plt.gca().spines.values():\n", " spine.set_visible(False)\n", "\n", " plt.xticks([0,1,2,3], ['Malignant\\nTraining', 'Benign\\nTraining', 'Malignant\\nTest', 'Benign\\nTest'], alpha=0.8);\n", " plt.title('Training and Test Accuracies for Malignant and Benign Cells', alpha=0.8)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Uncomment the plotting function to see the visualization.\n", "\n", "**Comment out** the plotting function when submitting your notebook for grading. " ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "data": { "application/javascript": [ "/* Put everything inside the global mpl namespace */\n", "window.mpl = {};\n", "\n", "\n", "mpl.get_websocket_type = function() {\n", " if (typeof(WebSocket) !== 'undefined') {\n", " return WebSocket;\n", " } else if (typeof(MozWebSocket) !== 'undefined') {\n", " return MozWebSocket;\n", " } else {\n", " alert('Your browser does not have WebSocket support.' +\n", " 'Please try Chrome, Safari or Firefox ≥ 6. ' +\n", " 'Firefox 4 and 5 are also supported but you ' +\n", " 'have to enable WebSockets in about:config.');\n", " };\n", "}\n", "\n", "mpl.figure = function(figure_id, websocket, ondownload, parent_element) {\n", " this.id = figure_id;\n", "\n", " this.ws = websocket;\n", "\n", " this.supports_binary = (this.ws.binaryType != undefined);\n", "\n", " if (!this.supports_binary) {\n", " var warnings = document.getElementById(\"mpl-warnings\");\n", " if (warnings) {\n", " warnings.style.display = 'block';\n", " warnings.textContent = (\n", " \"This browser does not support binary websocket messages. \" +\n", " \"Performance may be slow.\");\n", " }\n", " }\n", "\n", " this.imageObj = new Image();\n", "\n", " this.context = undefined;\n", " this.message = undefined;\n", " this.canvas = undefined;\n", " this.rubberband_canvas = undefined;\n", " this.rubberband_context = undefined;\n", " this.format_dropdown = undefined;\n", "\n", " this.image_mode = 'full';\n", "\n", " this.root = $('
');\n", " this._root_extra_style(this.root)\n", " this.root.attr('style', 'display: inline-block');\n", "\n", " $(parent_element).append(this.root);\n", "\n", " this._init_header(this);\n", " this._init_canvas(this);\n", " this._init_toolbar(this);\n", "\n", " var fig = this;\n", "\n", " this.waiting = false;\n", "\n", " this.ws.onopen = function () {\n", " fig.send_message(\"supports_binary\", {value: fig.supports_binary});\n", " fig.send_message(\"send_image_mode\", {});\n", " if (mpl.ratio != 1) {\n", " fig.send_message(\"set_dpi_ratio\", {'dpi_ratio': mpl.ratio});\n", " }\n", " fig.send_message(\"refresh\", {});\n", " }\n", "\n", " this.imageObj.onload = function() {\n", " if (fig.image_mode == 'full') {\n", " // Full images could contain transparency (where diff images\n", " // almost always do), so we need to clear the canvas so that\n", " // there is no ghosting.\n", " fig.context.clearRect(0, 0, fig.canvas.width, fig.canvas.height);\n", " }\n", " fig.context.drawImage(fig.imageObj, 0, 0);\n", " };\n", "\n", " this.imageObj.onunload = function() {\n", " this.ws.close();\n", " }\n", "\n", " this.ws.onmessage = this._make_on_message_function(this);\n", "\n", " this.ondownload = ondownload;\n", "}\n", "\n", "mpl.figure.prototype._init_header = function() {\n", " var titlebar = $(\n", " '
');\n", " var titletext = $(\n", " '
');\n", " titlebar.append(titletext)\n", " this.root.append(titlebar);\n", " this.header = titletext[0];\n", "}\n", "\n", "\n", "\n", "mpl.figure.prototype._canvas_extra_style = function(canvas_div) {\n", "\n", "}\n", "\n", "\n", "mpl.figure.prototype._root_extra_style = function(canvas_div) {\n", "\n", "}\n", "\n", "mpl.figure.prototype._init_canvas = function() {\n", " var fig = this;\n", "\n", " var canvas_div = $('
');\n", "\n", " canvas_div.attr('style', 'position: relative; clear: both; outline: 0');\n", "\n", " function canvas_keyboard_event(event) {\n", " return fig.key_event(event, event['data']);\n", " }\n", "\n", " canvas_div.keydown('key_press', canvas_keyboard_event);\n", " canvas_div.keyup('key_release', canvas_keyboard_event);\n", " this.canvas_div = canvas_div\n", " this._canvas_extra_style(canvas_div)\n", " this.root.append(canvas_div);\n", "\n", " var canvas = $('');\n", " canvas.addClass('mpl-canvas');\n", " canvas.attr('style', \"left: 0; top: 0; z-index: 0; outline: 0\")\n", "\n", " this.canvas = canvas[0];\n", " this.context = canvas[0].getContext(\"2d\");\n", "\n", " var backingStore = this.context.backingStorePixelRatio ||\n", "\tthis.context.webkitBackingStorePixelRatio ||\n", "\tthis.context.mozBackingStorePixelRatio ||\n", "\tthis.context.msBackingStorePixelRatio ||\n", "\tthis.context.oBackingStorePixelRatio ||\n", "\tthis.context.backingStorePixelRatio || 1;\n", "\n", " mpl.ratio = (window.devicePixelRatio || 1) / backingStore;\n", "\n", " var rubberband = $('');\n", " rubberband.attr('style', \"position: absolute; left: 0; top: 0; z-index: 1;\")\n", "\n", " var pass_mouse_events = true;\n", "\n", " canvas_div.resizable({\n", " start: function(event, ui) {\n", " pass_mouse_events = false;\n", " },\n", " resize: function(event, ui) {\n", " fig.request_resize(ui.size.width, ui.size.height);\n", " },\n", " stop: function(event, ui) {\n", " pass_mouse_events = true;\n", " fig.request_resize(ui.size.width, ui.size.height);\n", " },\n", " });\n", "\n", " function mouse_event_fn(event) {\n", " if (pass_mouse_events)\n", " return fig.mouse_event(event, event['data']);\n", " }\n", "\n", " rubberband.mousedown('button_press', mouse_event_fn);\n", " rubberband.mouseup('button_release', mouse_event_fn);\n", " // Throttle sequential mouse events to 1 every 20ms.\n", " rubberband.mousemove('motion_notify', mouse_event_fn);\n", "\n", " rubberband.mouseenter('figure_enter', mouse_event_fn);\n", " rubberband.mouseleave('figure_leave', mouse_event_fn);\n", "\n", " canvas_div.on(\"wheel\", function (event) {\n", " event = event.originalEvent;\n", " event['data'] = 'scroll'\n", " if (event.deltaY < 0) {\n", " event.step = 1;\n", " } else {\n", " event.step = -1;\n", " }\n", " mouse_event_fn(event);\n", " });\n", "\n", " canvas_div.append(canvas);\n", " canvas_div.append(rubberband);\n", "\n", " this.rubberband = rubberband;\n", " this.rubberband_canvas = rubberband[0];\n", " this.rubberband_context = rubberband[0].getContext(\"2d\");\n", " this.rubberband_context.strokeStyle = \"#000000\";\n", "\n", " this._resize_canvas = function(width, height) {\n", " // Keep the size of the canvas, canvas container, and rubber band\n", " // canvas in synch.\n", " canvas_div.css('width', width)\n", " canvas_div.css('height', height)\n", "\n", " canvas.attr('width', width * mpl.ratio);\n", " canvas.attr('height', height * mpl.ratio);\n", " canvas.attr('style', 'width: ' + width + 'px; height: ' + height + 'px;');\n", "\n", " rubberband.attr('width', width);\n", " rubberband.attr('height', height);\n", " }\n", "\n", " // Set the figure to an initial 600x600px, this will subsequently be updated\n", " // upon first draw.\n", " this._resize_canvas(600, 600);\n", "\n", " // Disable right mouse context menu.\n", " $(this.rubberband_canvas).bind(\"contextmenu\",function(e){\n", " return false;\n", " });\n", "\n", " function set_focus () {\n", " canvas.focus();\n", " canvas_div.focus();\n", " }\n", "\n", " window.setTimeout(set_focus, 100);\n", "}\n", "\n", "mpl.figure.prototype._init_toolbar = function() {\n", " var fig = this;\n", "\n", " var nav_element = $('
')\n", " nav_element.attr('style', 'width: 100%');\n", " this.root.append(nav_element);\n", "\n", " // Define a callback function for later on.\n", " function toolbar_event(event) {\n", " return fig.toolbar_button_onclick(event['data']);\n", " }\n", " function toolbar_mouse_event(event) {\n", " return fig.toolbar_button_onmouseover(event['data']);\n", " }\n", "\n", " for(var toolbar_ind in mpl.toolbar_items) {\n", " var name = mpl.toolbar_items[toolbar_ind][0];\n", " var tooltip = mpl.toolbar_items[toolbar_ind][1];\n", " var image = mpl.toolbar_items[toolbar_ind][2];\n", " var method_name = mpl.toolbar_items[toolbar_ind][3];\n", "\n", " if (!name) {\n", " // put a spacer in here.\n", " continue;\n", " }\n", " var button = $('