Skip to content
Permalink
master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?

6001CEM_V2_8677851/Gender_Income_Classification.ipynb

Go to file
 
 
Cannot retrieve contributors at this time
2675 lines (2675 sloc) 167 KB
Raw Blame
Open in GitHub Desktop
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "TPU",
"colab": {
"name": "Keras_Deep_Clasification.ipynb",
"provenance": [],
"collapsed_sections": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "VyZ3HqLdZy42",
"outputId": "eaa5c99b-8ea9-462b-826d-bec7e125cfb9"
},
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')"
],
"execution_count": 220,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "CzyLwSHXV0Uw"
},
"source": [
"import keras\n",
"from keras.models import Sequential\n",
"from keras.layers import Dense, Dropout\n",
"import pandas as pd\n",
"from pandas.plotting import scatter_matrix\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn import model_selection, preprocessing, metrics\n",
"from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, plot_confusion_matrix\n",
"from sklearn.preprocessing import LabelEncoder, OneHotEncoder, StandardScaler\n",
"import numpy as np\n",
"import math\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.metrics import roc_curve, auc, roc_auc_score\n",
"%matplotlib inline"
],
"execution_count": 221,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "xHiwyDRQWVpC"
},
"source": [
"Loading Dataset"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 424
},
"id": "AQDorIHNWTIf",
"outputId": "8c829edf-df24-45fa-daaf-e5255c82c953"
},
"source": [
"dataset = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/adult.data', delimiter=',')\n",
"dataset.head(450)"
],
"execution_count": 222,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>workclass</th>\n",
" <th>fnlwgt</th>\n",
" <th>education</th>\n",
" <th>education-num</th>\n",
" <th>marital-status</th>\n",
" <th>occupation</th>\n",
" <th>relationship</th>\n",
" <th>race</th>\n",
" <th>sex</th>\n",
" <th>capital-gain</th>\n",
" <th>capital-loss</th>\n",
" <th>hours-per-week</th>\n",
" <th>native-country</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>39</td>\n",
" <td>State-gov</td>\n",
" <td>77516</td>\n",
" <td>Bachelors</td>\n",
" <td>13</td>\n",
" <td>Never-married</td>\n",
" <td>Adm-clerical</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>2174</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>50</td>\n",
" <td>Self-emp-not-inc</td>\n",
" <td>83311</td>\n",
" <td>Bachelors</td>\n",
" <td>13</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Husband</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>13</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>38</td>\n",
" <td>Private</td>\n",
" <td>215646</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Divorced</td>\n",
" <td>Handlers-cleaners</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>53</td>\n",
" <td>Private</td>\n",
" <td>234721</td>\n",
" <td>11th</td>\n",
" <td>7</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Handlers-cleaners</td>\n",
" <td>Husband</td>\n",
" <td>Black</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>28</td>\n",
" <td>Private</td>\n",
" <td>338409</td>\n",
" <td>Bachelors</td>\n",
" <td>13</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Prof-specialty</td>\n",
" <td>Wife</td>\n",
" <td>Black</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>Cuba</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>445</th>\n",
" <td>20</td>\n",
" <td>Private</td>\n",
" <td>298227</td>\n",
" <td>Some-college</td>\n",
" <td>10</td>\n",
" <td>Never-married</td>\n",
" <td>Sales</td>\n",
" <td>Not-in-family</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>35</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>446</th>\n",
" <td>44</td>\n",
" <td>Private</td>\n",
" <td>290521</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Widowed</td>\n",
" <td>Exec-managerial</td>\n",
" <td>Unmarried</td>\n",
" <td>Black</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>447</th>\n",
" <td>51</td>\n",
" <td>Private</td>\n",
" <td>56915</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Craft-repair</td>\n",
" <td>Husband</td>\n",
" <td>Amer-Indian-Eskimo</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>448</th>\n",
" <td>20</td>\n",
" <td>Private</td>\n",
" <td>146538</td>\n",
" <td>HS-grad</td>\n",
" <td>9</td>\n",
" <td>Married-civ-spouse</td>\n",
" <td>Machine-op-inspct</td>\n",
" <td>Husband</td>\n",
" <td>White</td>\n",
" <td>Male</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" <tr>\n",
" <th>449</th>\n",
" <td>17</td>\n",
" <td>?</td>\n",
" <td>258872</td>\n",
" <td>11th</td>\n",
" <td>7</td>\n",
" <td>Never-married</td>\n",
" <td>?</td>\n",
" <td>Own-child</td>\n",
" <td>White</td>\n",
" <td>Female</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>5</td>\n",
" <td>United-States</td>\n",
" <td>&lt;=50K</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>450 rows × 15 columns</p>\n",
"</div>"
],
"text/plain": [
" age workclass fnlwgt ... hours-per-week native-country income\n",
"0 39 State-gov 77516 ... 40 United-States <=50K\n",
"1 50 Self-emp-not-inc 83311 ... 13 United-States <=50K\n",
"2 38 Private 215646 ... 40 United-States <=50K\n",
"3 53 Private 234721 ... 40 United-States <=50K\n",
"4 28 Private 338409 ... 40 Cuba <=50K\n",
".. ... ... ... ... ... ... ...\n",
"445 20 Private 298227 ... 35 United-States <=50K\n",
"446 44 Private 290521 ... 40 United-States <=50K\n",
"447 51 Private 56915 ... 40 United-States <=50K\n",
"448 20 Private 146538 ... 40 United-States <=50K\n",
"449 17 ? 258872 ... 5 United-States <=50K\n",
"\n",
"[450 rows x 15 columns]"
]
},
"metadata": {},
"execution_count": 222
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "BwZ_JDmk_OPx"
},
"source": [
"Bivariate Analysis"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 889
},
"id": "pXGjqDhI_OAR",
"outputId": "d234c393-6245-4f39-b55d-1926af253f43"
},
"source": [
"def plot_bivariate_bar(dataset, hue, cols=1, width=20, height=15, hspace=0.2, wspace=0.5):\n",
" dataset = dataset.select_dtypes(include=[np.object])\n",
" fig = plt.figure(figsize=(width,height))\n",
" plt.style.use('seaborn-whitegrid')\n",
" fig.subplots_adjust(left=None, bottom=None, right=None, top=None, wspace=wspace, hspace=hspace)\n",
" rows = math.ceil(float(dataset.shape[1]) / cols)\n",
" for i, column in enumerate(dataset.columns):\n",
" ax = fig.add_subplot(rows, cols, i + 1)\n",
" ax.set_title(column)\n",
" if dataset.dtypes[column] == np.object:\n",
" g = sns.countplot(y=column, hue=hue, data=dataset)\n",
" substrings = [s.get_text()[:10] for s in g.get_yticklabels()]\n",
" g.set(yticklabels=substrings)\n",
" plt.show()\n",
" \n",
"bivariate_df = dataset.reindex(columns = [' race', ' sex',' income'])\n",
"\n",
"plot_bivariate_bar(bivariate_df, hue=' income', cols=1, width=20, height=15, hspace=0.4, wspace=0.5)"
],
"execution_count": 223,
"outputs": [
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1440x1080 with 3 Axes>"
]
},
"metadata": {
"needs_background": "light"
}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vtY0ZpdjFLbJ"
},
"source": [
"Race to Income"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 348
},
"id": "nn2D_22UFRJP",
"outputId": "9fa0b8e5-47fe-40c8-d65c-0ae3b5f86f7f"
},
"source": [
"#def rece_to_income(race)\n",
"a4_dims = (20, 5)\n",
"fig, ax = plt.subplots(figsize=a4_dims)\n",
"ax = sns.violinplot(x = ' sex', y = 'age', hue = ' income',\n",
" data = dataset, gridsize = 100, palette = \"muted\", split = True, saturation = 0.75)\n",
"ax\n",
"#rece_to_income(' race_Black')\n",
"#rece_to_income(' race_White')\n",
"#rece_to_income(' race_Other')"
],
"execution_count": 224,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.axes._subplots.AxesSubplot at 0x7fabe50f37d0>"
]
},
"metadata": {},
"execution_count": 224
},
{
"output_type": "display_data",
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 1440x360 with 1 Axes>"
]
},
"metadata": {}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "42fd5_3bHmnU"
},
"source": [
"Normalization"
]
},
{
"cell_type": "code",
"metadata": {
"id": "5AcERCH9WrQ9"
},
"source": [
"columns = dataset.columns\n",
"for col in columns:\n",
"\tdataset[col] = dataset[col].replace(\"?\", np.NaN)\n",
"\n",
"dataset = dataset.fillna(dataset.mode().iloc[0])"
],
"execution_count": 225,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "vSRTAmu9a4hN"
},
"source": [
"dataset.replace(to_replace=['Divorced'],value=['divorced'],inplace=True)\n",
"dataset.replace(to_replace=['Married-AF-spouse', 'Married-civ-spouse', 'Married-spouse-absent'],value='married',inplace=True)\n",
"dataset.replace(to_replace=['Never-married','Separated','Widowed'],value='not married',inplace=True)"
],
"execution_count": 226,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 795
},
"id": "12biFAH6qEyi",
"outputId": "6e9d1a61-556a-4d0d-9aea-824bca7732f5"
},
"source": [
"lab_en = preprocessing.LabelEncoder()\n",
"cat_column = [' marital-status', ' income'] \n",
"\n",
"for col in cat_column:\n",
" dataset[col] = lab_en.fit_transform(dataset[col])\n",
"\n",
"category_col_1 = [' race', ' sex', ' workclass', ' education', ' occupation', ' relationship',' native-country'] \n",
"dataset_2 = pd.get_dummies(dataset, columns=category_col_1, drop_first=True)\n",
"\n",
"##unknown Attribute is removed and income class label is appended in the end\n",
"data_frame = dataset_2.drop(' fnlwgt',1)\n",
"data_frame = data_frame[[c for c in data_frame if c not in [' income']] + [' income']]\n",
"data_frame.head(20)"
],
"execution_count": 227,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>age</th>\n",
" <th>education-num</th>\n",
" <th>marital-status</th>\n",
" <th>capital-gain</th>\n",
" <th>capital-loss</th>\n",
" <th>hours-per-week</th>\n",
" <th>race_ Asian-Pac-Islander</th>\n",
" <th>race_ Black</th>\n",
" <th>race_ Other</th>\n",
" <th>race_ White</th>\n",
" <th>sex_ Male</th>\n",
" <th>workclass_ Federal-gov</th>\n",
" <th>workclass_ Local-gov</th>\n",
" <th>workclass_ Never-worked</th>\n",
" <th>workclass_ Private</th>\n",
" <th>workclass_ Self-emp-inc</th>\n",
" <th>workclass_ Self-emp-not-inc</th>\n",
" <th>workclass_ State-gov</th>\n",
" <th>workclass_ Without-pay</th>\n",
" <th>education_ 11th</th>\n",
" <th>education_ 12th</th>\n",
" <th>education_ 1st-4th</th>\n",
" <th>education_ 5th-6th</th>\n",
" <th>education_ 7th-8th</th>\n",
" <th>education_ 9th</th>\n",
" <th>education_ Assoc-acdm</th>\n",
" <th>education_ Assoc-voc</th>\n",
" <th>education_ Bachelors</th>\n",
" <th>education_ Doctorate</th>\n",
" <th>education_ HS-grad</th>\n",
" <th>education_ Masters</th>\n",
" <th>education_ Preschool</th>\n",
" <th>education_ Prof-school</th>\n",
" <th>education_ Some-college</th>\n",
" <th>occupation_ Adm-clerical</th>\n",
" <th>occupation_ Armed-Forces</th>\n",
" <th>occupation_ Craft-repair</th>\n",
" <th>occupation_ Exec-managerial</th>\n",
" <th>occupation_ Farming-fishing</th>\n",
" <th>occupation_ Handlers-cleaners</th>\n",
" <th>...</th>\n",
" <th>native-country_ China</th>\n",
" <th>native-country_ Columbia</th>\n",
" <th>native-country_ Cuba</th>\n",
" <th>native-country_ Dominican-Republic</th>\n",
" <th>native-country_ Ecuador</th>\n",
" <th>native-country_ El-Salvador</th>\n",
" <th>native-country_ England</th>\n",
" <th>native-country_ France</th>\n",
" <th>native-country_ Germany</th>\n",
" <th>native-country_ Greece</th>\n",
" <th>native-country_ Guatemala</th>\n",
" <th>native-country_ Haiti</th>\n",
" <th>native-country_ Holand-Netherlands</th>\n",
" <th>native-country_ Honduras</th>\n",
" <th>native-country_ Hong</th>\n",
" <th>native-country_ Hungary</th>\n",
" <th>native-country_ India</th>\n",
" <th>native-country_ Iran</th>\n",
" <th>native-country_ Ireland</th>\n",
" <th>native-country_ Italy</th>\n",
" <th>native-country_ Jamaica</th>\n",
" <th>native-country_ Japan</th>\n",
" <th>native-country_ Laos</th>\n",
" <th>native-country_ Mexico</th>\n",
" <th>native-country_ Nicaragua</th>\n",
" <th>native-country_ Outlying-US(Guam-USVI-etc)</th>\n",
" <th>native-country_ Peru</th>\n",
" <th>native-country_ Philippines</th>\n",
" <th>native-country_ Poland</th>\n",
" <th>native-country_ Portugal</th>\n",
" <th>native-country_ Puerto-Rico</th>\n",
" <th>native-country_ Scotland</th>\n",
" <th>native-country_ South</th>\n",
" <th>native-country_ Taiwan</th>\n",
" <th>native-country_ Thailand</th>\n",
" <th>native-country_ Trinadad&amp;Tobago</th>\n",
" <th>native-country_ United-States</th>\n",
" <th>native-country_ Vietnam</th>\n",
" <th>native-country_ Yugoslavia</th>\n",
" <th>income</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>39</td>\n",
" <td>13</td>\n",
" <td>4</td>\n",
" <td>2174</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>50</td>\n",
" <td>13</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>13</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>38</td>\n",
" <td>9</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>53</td>\n",
" <td>7</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>28</td>\n",
" <td>13</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>37</td>\n",
" <td>14</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>49</td>\n",
" <td>5</td>\n",
" <td>3</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>16</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>52</td>\n",
" <td>9</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>45</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>31</td>\n",
" <td>14</td>\n",
" <td>4</td>\n",
" <td>14084</td>\n",
" <td>0</td>\n",
" <td>50</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>42</td>\n",
" <td>13</td>\n",
" <td>2</td>\n",
" <td>5178</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>37</td>\n",
" <td>10</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>80</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>30</td>\n",
" <td>13</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>23</td>\n",
" <td>13</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>30</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>32</td>\n",
" <td>12</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>50</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>40</td>\n",
" <td>11</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>34</td>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>45</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>25</td>\n",
" <td>9</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>35</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>32</td>\n",
" <td>9</td>\n",
" <td>4</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>40</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>38</td>\n",
" <td>7</td>\n",
" <td>2</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>50</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>43</td>\n",
" <td>14</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>45</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>20 rows × 95 columns</p>\n",
"</div>"
],
"text/plain": [
" age education-num ... native-country_ Yugoslavia income\n",
"0 39 13 ... 0 0\n",
"1 50 13 ... 0 0\n",
"2 38 9 ... 0 0\n",
"3 53 7 ... 0 0\n",
"4 28 13 ... 0 0\n",
"5 37 14 ... 0 0\n",
"6 49 5 ... 0 0\n",
"7 52 9 ... 0 1\n",
"8 31 14 ... 0 1\n",
"9 42 13 ... 0 1\n",
"10 37 10 ... 0 1\n",
"11 30 13 ... 0 1\n",
"12 23 13 ... 0 0\n",
"13 32 12 ... 0 0\n",
"14 40 11 ... 0 1\n",
"15 34 4 ... 0 0\n",
"16 25 9 ... 0 0\n",
"17 32 9 ... 0 0\n",
"18 38 7 ... 0 0\n",
"19 43 14 ... 0 1\n",
"\n",
"[20 rows x 95 columns]"
]
},
"metadata": {},
"execution_count": 227
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "NvWqvF7Gq6HZ",
"outputId": "48bdc3e6-b331-48be-e4d7-b497f3df77b6"
},
"source": [
"labels = data_frame[' income']\n",
"features = data_frame.iloc[:,9:11]\n",
"\n",
"X=features\n",
"y=np.ravel(labels)\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)\n",
"print(X,y)\n",
"scaler = StandardScaler().fit(X_train)\n",
"X_train = scaler.transform(X_train)\n",
"X_test = scaler.transform(X_test) "
],
"execution_count": 228,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
" race_ White sex_ Male\n",
"0 1 1\n",
"1 1 1\n",
"2 1 1\n",
"3 0 1\n",
"4 0 0\n",
"... ... ...\n",
"32556 1 0\n",
"32557 1 1\n",
"32558 1 0\n",
"32559 1 1\n",
"32560 1 0\n",
"\n",
"[32561 rows x 2 columns] [0 0 0 ... 0 0 1]\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "tSLLYyOBrBjk"
},
"source": [
"# Support Vector Classifier (SVM/SVC)"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "LYOhOOpErDIx",
"outputId": "eccbcb81-64fc-4e54-a8ff-1089d8fb0cdc"
},
"source": [
"from sklearn.svm import SVC\n",
"svc = SVC(gamma=0.22)\n",
"svc.fit(X_train, y_train)\n",
"#y_pred = logreg.predict(X_test)\n",
"score_svc = svc.score(X_test,y_test)\n",
"print('The accuracy of SVC Model is', str(round(score_svc*100, 2)) + '%')"
],
"execution_count": 242,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The accuracy of SVC Model is 51.37%\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "G5CD-H4yry9S"
},
"source": [
"#K-Nearest Neighbors"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "aDbND84jr3Jy",
"outputId": "a1d383c7-cb36-4cd6-d8b9-e735ccb0acee"
},
"source": [
"from sklearn.neighbors import KNeighborsClassifier #KNN\n",
"knn = KNeighborsClassifier()\n",
"knn.fit(X_train, y_train)\n",
"#y_pred = knn.predict(X_test)\n",
"score_knn = knn.score(X_test,y_test)\n",
"print('The accuracy of the KNN Model is', str(round(score_knn*100, 2)) + '%')"
],
"execution_count": 243,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The accuracy of the KNN Model is 35.36%\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "WpBT4QXLrZjl"
},
"source": [
"#Neural Model"
]
},
{
"cell_type": "code",
"metadata": {
"id": "r3jgUVqQrAhU",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "c05ee1c2-ebc3-4573-d2bc-563b0fd5c85a"
},
"source": [
"model = Sequential()\n",
"\n",
"model.add(Dense(4, activation='relu', input_shape=(2,)))\n",
"model.add(Dense(16, activation='relu'))\n",
"model.add(Dropout(0.5))\n",
"model.add(Dense(8, activation='relu'))\n",
"model.add(Dropout(0.75))\n",
"model.add(Dense(1, activation='sigmoid'))\n",
"model.compile(optimizer = 'nadam', loss = 'mean_squared_error', metrics=[\"binary_accuracy\"])\n",
" \n",
"model.fit(X_train, y_train, epochs=6, batch_size=2)\n",
"\n",
"y_pred = model.predict(X_test)\n",
"y_pred = (y_pred > 0.5)"
],
"execution_count": 232,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/6\n",
"10908/10908 [==============================] - 23s 2ms/step - loss: 0.1869 - binary_accuracy: 0.7542\n",
"Epoch 2/6\n",
"10908/10908 [==============================] - 22s 2ms/step - loss: 0.1796 - binary_accuracy: 0.7575\n",
"Epoch 3/6\n",
"10908/10908 [==============================] - 21s 2ms/step - loss: 0.1793 - binary_accuracy: 0.7575\n",
"Epoch 4/6\n",
"10908/10908 [==============================] - 21s 2ms/step - loss: 0.1790 - binary_accuracy: 0.7575\n",
"Epoch 5/6\n",
"10908/10908 [==============================] - 21s 2ms/step - loss: 0.1791 - binary_accuracy: 0.7574\n",
"Epoch 6/6\n",
"10908/10908 [==============================] - 21s 2ms/step - loss: 0.1790 - binary_accuracy: 0.7575\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iNcsoulDhWhP"
},
"source": [
"Model Evaluation"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "kwRQd2N4hdEG",
"outputId": "bbc69c5e-11ab-4993-af68-b23a48e21664"
},
"source": [
"scores = model.evaluate(X_test, y_test)\n",
"print(model.metrics_names)\n",
"print(scores)\n",
"print(\"\\n%s: %.2f%%\" % (model.metrics_names[1], scores[1]*100))"
],
"execution_count": 238,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"336/336 [==============================] - 0s 1ms/step - loss: 0.1937 - binary_accuracy: 0.7123\n",
"['loss', 'binary_accuracy']\n",
"[0.1937405718237464, 0.7123910472638472] \n",
"\n",
"binary_accuracy: 71.23%\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "QcIM3terh3N7"
},
"source": [
"Plotting Confusion Matrix"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "OcDYwyiHh6UR",
"outputId": "ec77d2d6-f854-450c-e9dc-e7a0f6dec46c"
},
"source": [
"y_pred = model.predict(X_test)\n",
"y_pred = (y_pred > 0.5)\n",
"cm = confusion_matrix(y_test, y_pred)\n",
"print(\"\\n Confusion Matrix: \\n\", cm)"
],
"execution_count": 239,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" Confusion Matrix: \n",
" [[8196 0]\n",
" [2550 0]]\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xhXPvl0fU_vw",
"outputId": "55341fac-fb55-48af-b1fb-48258faa03f1"
},
"source": [
"cmn = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]\n",
"print(cmn)"
],
"execution_count": 240,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"[[1. 0.]\n",
" [1. 0.]]\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VH38ZS5gRjVJ"
},
"source": [
"Receiver Operator Characteristics (ROC) curve"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "p0apd709SM1h"
},
"source": [
" Calculate the area under the ROC curve"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "ss3Z-n9qRw2J",
"outputId": "b23db328-9aec-472e-fff7-8ffd8b18c38e"
},
"source": [
"r_auc = roc_auc_score(y_test, y_pred)\n",
"print(\"Random chance prediction score: %.3f\" % (r_auc))"
],
"execution_count": 241,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Random chance prediction score: 0.500\n"
]
}
]
}
]
}