mlessentials/Lab11/Exercise11.01/Exercise11_01.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "HEiOAwQPW0qb"
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "j7whidfaYjns"
   },
   "outputs": [],
   "source": [
    "file_url = '../dataset/breast-cancer-wisconsin.data'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "nFMz2jNVt-xy"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(file_url, header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "Ysg_abDDATWd"
   },
   "outputs": [],
   "source": [
    "col_names = ['Sample code number','Clump Thickness','Uniformity of Cell Size','Uniformity of Cell Shape','Marginal Adhesion','Single Epithelial Cell Size',\n",
    "'Bare Nuclei','Bland Chromatin','Normal Nucleoli','Mitoses','Class']                  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "VwROQvaMHWUq"
   },
   "outputs": [],
   "source": [
    "df.columns = col_names"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "jpSNmaLTI0Tc",
    "outputId": "5c2b15a8-0cb1-4952-97cf-a3634bd4fd23"
   },
   "outputs": [],
   "source": [
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 221
    },
    "colab_type": "code",
    "id": "FtMSHk6cHgwK",
    "outputId": "e52b0624-a90b-4615-a30f-d149d8a41f55"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "5aPvl9bpuL5R",
    "outputId": "89abe994-3cf8-4210-96ab-7b3d8c8f470e"
   },
   "outputs": [],
   "source": [
    "df.duplicated().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 314
    },
    "colab_type": "code",
    "id": "YZQGk3-uH-uw",
    "outputId": "157d6c5a-1ece-4f0d-e435-074b775207ac"
   },
   "outputs": [],
   "source": [
    "df.loc[df.duplicated()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 314
    },
    "colab_type": "code",
    "id": "s27zOqKmIKd0",
    "outputId": "52c71d13-4b6a-4302-cbb9-0dc31cb14d48"
   },
   "outputs": [],
   "source": [
    "df.loc[df.duplicated(keep='last')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "SoNSF72yIfl6"
   },
   "outputs": [],
   "source": [
    "df_unique = df.drop_duplicates(keep='first')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "id": "-NBl7SK9JWKa",
    "outputId": "feddf245-061b-4cf9-9d78-748fc675ffde"
   },
   "outputs": [],
   "source": [
    "df_unique.shape"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise11.01.ipynb",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}