1141 lines
188 KiB
Plaintext
1141 lines
188 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 1,
|
||
|
|
"id": "9e96a1dd-303c-4920-8d24-d5d7e58dc02d",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"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>sepal length (cm)</th>\n",
|
||
|
|
" <th>sepal width (cm)</th>\n",
|
||
|
|
" <th>petal length (cm)</th>\n",
|
||
|
|
" <th>petal width (cm)</th>\n",
|
||
|
|
" <th>Species</th>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </thead>\n",
|
||
|
|
" <tbody>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>0</th>\n",
|
||
|
|
" <td>5.1</td>\n",
|
||
|
|
" <td>3.5</td>\n",
|
||
|
|
" <td>1.4</td>\n",
|
||
|
|
" <td>0.2</td>\n",
|
||
|
|
" <td>Iris-setosa</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>1</th>\n",
|
||
|
|
" <td>4.9</td>\n",
|
||
|
|
" <td>3.0</td>\n",
|
||
|
|
" <td>1.4</td>\n",
|
||
|
|
" <td>0.2</td>\n",
|
||
|
|
" <td>Iris-setosa</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>2</th>\n",
|
||
|
|
" <td>4.7</td>\n",
|
||
|
|
" <td>3.2</td>\n",
|
||
|
|
" <td>1.3</td>\n",
|
||
|
|
" <td>0.2</td>\n",
|
||
|
|
" <td>Iris-setosa</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>3</th>\n",
|
||
|
|
" <td>4.6</td>\n",
|
||
|
|
" <td>3.1</td>\n",
|
||
|
|
" <td>1.5</td>\n",
|
||
|
|
" <td>0.2</td>\n",
|
||
|
|
" <td>Iris-setosa</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>4</th>\n",
|
||
|
|
" <td>5.0</td>\n",
|
||
|
|
" <td>3.6</td>\n",
|
||
|
|
" <td>1.4</td>\n",
|
||
|
|
" <td>0.2</td>\n",
|
||
|
|
" <td>Iris-setosa</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </tbody>\n",
|
||
|
|
"</table>\n",
|
||
|
|
"</div>"
|
||
|
|
],
|
||
|
|
"text/plain": [
|
||
|
|
" sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) \\\n",
|
||
|
|
"0 5.1 3.5 1.4 0.2 \n",
|
||
|
|
"1 4.9 3.0 1.4 0.2 \n",
|
||
|
|
"2 4.7 3.2 1.3 0.2 \n",
|
||
|
|
"3 4.6 3.1 1.5 0.2 \n",
|
||
|
|
"4 5.0 3.6 1.4 0.2 \n",
|
||
|
|
"\n",
|
||
|
|
" Species \n",
|
||
|
|
"0 Iris-setosa \n",
|
||
|
|
"1 Iris-setosa \n",
|
||
|
|
"2 Iris-setosa \n",
|
||
|
|
"3 Iris-setosa \n",
|
||
|
|
"4 Iris-setosa "
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 1,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"\n",
|
||
|
|
"# Loading the iris dataset\n",
|
||
|
|
"url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data\"\n",
|
||
|
|
"df = pd.read_csv(url, header=None, names=['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)',\n",
|
||
|
|
" 'petal width (cm)', 'Species'])\n",
|
||
|
|
"df.head()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 2,
|
||
|
|
"id": "1a8f6c2f-d63a-4fc0-9e06-3c360e451852",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"(150, 5)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 2,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# To know number of rows and collumns\n",
|
||
|
|
"df.shape"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 3,
|
||
|
|
"id": "dc5283cb-d268-4373-99d1-94cf90c33edd",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
||
|
|
"RangeIndex: 150 entries, 0 to 149\n",
|
||
|
|
"Data columns (total 5 columns):\n",
|
||
|
|
" # Column Non-Null Count Dtype \n",
|
||
|
|
"--- ------ -------------- ----- \n",
|
||
|
|
" 0 sepal length (cm) 150 non-null float64\n",
|
||
|
|
" 1 sepal width (cm) 150 non-null float64\n",
|
||
|
|
" 2 petal length (cm) 150 non-null float64\n",
|
||
|
|
" 3 petal width (cm) 150 non-null float64\n",
|
||
|
|
" 4 Species 150 non-null object \n",
|
||
|
|
"dtypes: float64(4), object(1)\n",
|
||
|
|
"memory usage: 6.0+ KB\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# Check the dataframe information\n",
|
||
|
|
"df.info()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 4,
|
||
|
|
"id": "68c02ddc-9a88-45b1-8f86-9b2c9ebfc713",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"sepal length (cm) 0\n",
|
||
|
|
"sepal width (cm) 0\n",
|
||
|
|
"petal length (cm) 0\n",
|
||
|
|
"petal width (cm) 0\n",
|
||
|
|
"Species 0\n",
|
||
|
|
"dtype: int64"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 4,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# To find if any null value is present\n",
|
||
|
|
"df.isnull().sum()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 5,
|
||
|
|
"id": "15fa05e3-9e35-44dc-a053-4021f64ec00b",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"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>count</th>\n",
|
||
|
|
" <th>mean</th>\n",
|
||
|
|
" <th>std</th>\n",
|
||
|
|
" <th>min</th>\n",
|
||
|
|
" <th>25%</th>\n",
|
||
|
|
" <th>50%</th>\n",
|
||
|
|
" <th>75%</th>\n",
|
||
|
|
" <th>max</th>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </thead>\n",
|
||
|
|
" <tbody>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>sepal length (cm)</th>\n",
|
||
|
|
" <td>150.0</td>\n",
|
||
|
|
" <td>5.843333</td>\n",
|
||
|
|
" <td>0.828066</td>\n",
|
||
|
|
" <td>4.3</td>\n",
|
||
|
|
" <td>5.1</td>\n",
|
||
|
|
" <td>5.80</td>\n",
|
||
|
|
" <td>6.4</td>\n",
|
||
|
|
" <td>7.9</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>sepal width (cm)</th>\n",
|
||
|
|
" <td>150.0</td>\n",
|
||
|
|
" <td>3.054000</td>\n",
|
||
|
|
" <td>0.433594</td>\n",
|
||
|
|
" <td>2.0</td>\n",
|
||
|
|
" <td>2.8</td>\n",
|
||
|
|
" <td>3.00</td>\n",
|
||
|
|
" <td>3.3</td>\n",
|
||
|
|
" <td>4.4</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>petal length (cm)</th>\n",
|
||
|
|
" <td>150.0</td>\n",
|
||
|
|
" <td>3.758667</td>\n",
|
||
|
|
" <td>1.764420</td>\n",
|
||
|
|
" <td>1.0</td>\n",
|
||
|
|
" <td>1.6</td>\n",
|
||
|
|
" <td>4.35</td>\n",
|
||
|
|
" <td>5.1</td>\n",
|
||
|
|
" <td>6.9</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" <tr>\n",
|
||
|
|
" <th>petal width (cm)</th>\n",
|
||
|
|
" <td>150.0</td>\n",
|
||
|
|
" <td>1.198667</td>\n",
|
||
|
|
" <td>0.763161</td>\n",
|
||
|
|
" <td>0.1</td>\n",
|
||
|
|
" <td>0.3</td>\n",
|
||
|
|
" <td>1.30</td>\n",
|
||
|
|
" <td>1.8</td>\n",
|
||
|
|
" <td>2.5</td>\n",
|
||
|
|
" </tr>\n",
|
||
|
|
" </tbody>\n",
|
||
|
|
"</table>\n",
|
||
|
|
"</div>"
|
||
|
|
],
|
||
|
|
"text/plain": [
|
||
|
|
" count mean std min 25% 50% 75% max\n",
|
||
|
|
"sepal length (cm) 150.0 5.843333 0.828066 4.3 5.1 5.80 6.4 7.9\n",
|
||
|
|
"sepal width (cm) 150.0 3.054000 0.433594 2.0 2.8 3.00 3.3 4.4\n",
|
||
|
|
"petal length (cm) 150.0 3.758667 1.764420 1.0 1.6 4.35 5.1 6.9\n",
|
||
|
|
"petal width (cm) 150.0 1.198667 0.763161 0.1 0.3 1.30 1.8 2.5"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 5,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# To see summary statistics\n",
|
||
|
|
"df.describe().T"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "markdown",
|
||
|
|
"id": "25225fd1-313b-4dd7-81e4-63e8a09490db",
|
||
|
|
"metadata": {},
|
||
|
|
"source": [
|
||
|
|
"### other options for palettes \n",
|
||
|
|
"\n",
|
||
|
|
"- \"PRGn\" \n",
|
||
|
|
"- \"flare\"\n",
|
||
|
|
"- \"colorblind\""
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 8,
|
||
|
|
"id": "6baff895-78f5-4c65-a804-32b372f95814",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 1900x1000 with 4 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import seaborn as sns\n",
|
||
|
|
"import matplotlib.pyplot as plt\n",
|
||
|
|
"#%matplotlib inline # inline render graphs below cell (but maybe not necessary anymore) \n",
|
||
|
|
"\n",
|
||
|
|
"columns = df.columns # my data has 4 columns.\n",
|
||
|
|
"\n",
|
||
|
|
"fig, ax = plt.subplots(ncols = 4, figsize=(19,10))\n",
|
||
|
|
"plt.subplots_adjust(wspace = 0.5) # wspace = width space\n",
|
||
|
|
"\n",
|
||
|
|
"for i in range(0,4):\n",
|
||
|
|
" s = sns.boxplot(ax = ax[i], data = df[columns[i]], showfliers = True)\n",
|
||
|
|
" ax[i].set_xlabel(columns[i])\n",
|
||
|
|
"\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 9,
|
||
|
|
"id": "32b155aa-a95b-438d-a0ee-0d1336bc462d",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"(146, 5)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 9,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
" # To remove outliers from 'sepal width (cm)'\n",
|
||
|
|
"q1 = df['sepal width (cm)'].quantile(0.25)\n",
|
||
|
|
"q3 = df['sepal width (cm)'].quantile(0.75)\n",
|
||
|
|
"iqr = q3 - q1\n",
|
||
|
|
"df = df[(df['sepal width (cm)'] >= q1-1.5*iqr) & (df['sepal width (cm)'] <= q3+1.5*iqr)]\n",
|
||
|
|
"df.shape # To find out the number of rows and column after outlier treatment"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 10,
|
||
|
|
"id": "665e444d-3d65-4dc6-94c1-60fb0677dc77",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 640x480 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"# Boxplot for sepal width (cm) after outlier treatment\n",
|
||
|
|
"sns.boxplot(y=df['sepal width (cm)'])\n",
|
||
|
|
"plt.show()"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 11,
|
||
|
|
"id": "4e7a2ded-1e62-479f-82c9-2fe73e2af3b7",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.model_selection import train_test_split\n",
|
||
|
|
"\n",
|
||
|
|
"# Splitting the data into train and test sets\n",
|
||
|
|
"X = df.drop(\"Species\",axis=1)\n",
|
||
|
|
"y = df[\"Species\"]\n",
|
||
|
|
"X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3, random_state= 1)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 12,
|
||
|
|
"id": "139a1941-1c75-4ead-81ed-83031c9f3ad6",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/html": [
|
||
|
|
"<style>#sk-container-id-1 {\n",
|
||
|
|
" /* Definition of color scheme common for light and dark mode */\n",
|
||
|
|
" --sklearn-color-text: black;\n",
|
||
|
|
" --sklearn-color-line: gray;\n",
|
||
|
|
" /* Definition of color scheme for unfitted estimators */\n",
|
||
|
|
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
|
||
|
|
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
|
||
|
|
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
|
||
|
|
" --sklearn-color-unfitted-level-3: chocolate;\n",
|
||
|
|
" /* Definition of color scheme for fitted estimators */\n",
|
||
|
|
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
|
||
|
|
" --sklearn-color-fitted-level-1: #d4ebff;\n",
|
||
|
|
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
|
||
|
|
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
|
||
|
|
"\n",
|
||
|
|
" /* Specific color for light theme */\n",
|
||
|
|
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
||
|
|
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
|
||
|
|
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
|
||
|
|
" --sklearn-color-icon: #696969;\n",
|
||
|
|
"\n",
|
||
|
|
" @media (prefers-color-scheme: dark) {\n",
|
||
|
|
" /* Redefinition of color scheme for dark theme */\n",
|
||
|
|
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
||
|
|
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
|
||
|
|
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
|
||
|
|
" --sklearn-color-icon: #878787;\n",
|
||
|
|
" }\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 {\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 pre {\n",
|
||
|
|
" padding: 0;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 input.sk-hidden--visually {\n",
|
||
|
|
" border: 0;\n",
|
||
|
|
" clip: rect(1px 1px 1px 1px);\n",
|
||
|
|
" clip: rect(1px, 1px, 1px, 1px);\n",
|
||
|
|
" height: 1px;\n",
|
||
|
|
" margin: -1px;\n",
|
||
|
|
" overflow: hidden;\n",
|
||
|
|
" padding: 0;\n",
|
||
|
|
" position: absolute;\n",
|
||
|
|
" width: 1px;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
|
||
|
|
" border: 1px dashed var(--sklearn-color-line);\n",
|
||
|
|
" margin: 0 0.4em 0.5em 0.4em;\n",
|
||
|
|
" box-sizing: border-box;\n",
|
||
|
|
" padding-bottom: 0.4em;\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-container {\n",
|
||
|
|
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
|
||
|
|
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
|
||
|
|
" so we also need the `!important` here to be able to override the\n",
|
||
|
|
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
|
||
|
|
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
|
||
|
|
" display: inline-block !important;\n",
|
||
|
|
" position: relative;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
|
||
|
|
" display: none;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"div.sk-parallel-item,\n",
|
||
|
|
"div.sk-serial,\n",
|
||
|
|
"div.sk-item {\n",
|
||
|
|
" /* draw centered vertical line to link estimators */\n",
|
||
|
|
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
|
||
|
|
" background-size: 2px 100%;\n",
|
||
|
|
" background-repeat: no-repeat;\n",
|
||
|
|
" background-position: center center;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Parallel-specific style estimator block */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel-item::after {\n",
|
||
|
|
" content: \"\";\n",
|
||
|
|
" width: 100%;\n",
|
||
|
|
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
|
||
|
|
" flex-grow: 1;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel {\n",
|
||
|
|
" display: flex;\n",
|
||
|
|
" align-items: stretch;\n",
|
||
|
|
" justify-content: center;\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
" position: relative;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel-item {\n",
|
||
|
|
" display: flex;\n",
|
||
|
|
" flex-direction: column;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
|
||
|
|
" align-self: flex-end;\n",
|
||
|
|
" width: 50%;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
|
||
|
|
" align-self: flex-start;\n",
|
||
|
|
" width: 50%;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
|
||
|
|
" width: 0;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Serial-specific style estimator block */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-serial {\n",
|
||
|
|
" display: flex;\n",
|
||
|
|
" flex-direction: column;\n",
|
||
|
|
" align-items: center;\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
" padding-right: 1em;\n",
|
||
|
|
" padding-left: 1em;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
|
||
|
|
"clickable and can be expanded/collapsed.\n",
|
||
|
|
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
|
||
|
|
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
|
||
|
|
"*/\n",
|
||
|
|
"\n",
|
||
|
|
"/* Pipeline and ColumnTransformer style (default) */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-toggleable {\n",
|
||
|
|
" /* Default theme specific background. It is overwritten whether we have a\n",
|
||
|
|
" specific estimator or a Pipeline/ColumnTransformer */\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Toggleable label */\n",
|
||
|
|
"#sk-container-id-1 label.sk-toggleable__label {\n",
|
||
|
|
" cursor: pointer;\n",
|
||
|
|
" display: block;\n",
|
||
|
|
" width: 100%;\n",
|
||
|
|
" margin-bottom: 0;\n",
|
||
|
|
" padding: 0.5em;\n",
|
||
|
|
" box-sizing: border-box;\n",
|
||
|
|
" text-align: center;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
|
||
|
|
" /* Arrow on the left of the label */\n",
|
||
|
|
" content: \"▸\";\n",
|
||
|
|
" float: left;\n",
|
||
|
|
" margin-right: 0.25em;\n",
|
||
|
|
" color: var(--sklearn-color-icon);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Toggleable content - dropdown */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-toggleable__content {\n",
|
||
|
|
" max-height: 0;\n",
|
||
|
|
" max-width: 0;\n",
|
||
|
|
" overflow: hidden;\n",
|
||
|
|
" text-align: left;\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
|
||
|
|
" margin: 0.2em;\n",
|
||
|
|
" border-radius: 0.25em;\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
|
||
|
|
" /* Expand drop-down */\n",
|
||
|
|
" max-height: 200px;\n",
|
||
|
|
" max-width: 100%;\n",
|
||
|
|
" overflow: auto;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
|
||
|
|
" content: \"▾\";\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Pipeline/ColumnTransformer-specific style */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Estimator-specific style */\n",
|
||
|
|
"\n",
|
||
|
|
"/* Colorize estimator box */\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
|
||
|
|
"#sk-container-id-1 div.sk-label label {\n",
|
||
|
|
" /* The background is the default theme color */\n",
|
||
|
|
" color: var(--sklearn-color-text-on-default-background);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* On hover, darken the color of the background */\n",
|
||
|
|
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Label box, darken color on hover, fitted */\n",
|
||
|
|
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Estimator label */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-label label {\n",
|
||
|
|
" font-family: monospace;\n",
|
||
|
|
" font-weight: bold;\n",
|
||
|
|
" display: inline-block;\n",
|
||
|
|
" line-height: 1.2em;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-label-container {\n",
|
||
|
|
" text-align: center;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Estimator-specific */\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator {\n",
|
||
|
|
" font-family: monospace;\n",
|
||
|
|
" border: 1px dotted var(--sklearn-color-border-box);\n",
|
||
|
|
" border-radius: 0.25em;\n",
|
||
|
|
" box-sizing: border-box;\n",
|
||
|
|
" margin-bottom: 0.5em;\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator.fitted {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-0);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* on hover */\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator:hover {\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-2);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
|
||
|
|
"\n",
|
||
|
|
"/* Common style for \"i\" and \"?\" */\n",
|
||
|
|
"\n",
|
||
|
|
".sk-estimator-doc-link,\n",
|
||
|
|
"a:link.sk-estimator-doc-link,\n",
|
||
|
|
"a:visited.sk-estimator-doc-link {\n",
|
||
|
|
" float: right;\n",
|
||
|
|
" font-size: smaller;\n",
|
||
|
|
" line-height: 1em;\n",
|
||
|
|
" font-family: monospace;\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
" border-radius: 1em;\n",
|
||
|
|
" height: 1em;\n",
|
||
|
|
" width: 1em;\n",
|
||
|
|
" text-decoration: none !important;\n",
|
||
|
|
" margin-left: 1ex;\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
||
|
|
" color: var(--sklearn-color-unfitted-level-1);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
".sk-estimator-doc-link.fitted,\n",
|
||
|
|
"a:link.sk-estimator-doc-link.fitted,\n",
|
||
|
|
"a:visited.sk-estimator-doc-link.fitted {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
||
|
|
" color: var(--sklearn-color-fitted-level-1);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* On hover */\n",
|
||
|
|
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
|
||
|
|
".sk-estimator-doc-link:hover,\n",
|
||
|
|
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
|
||
|
|
".sk-estimator-doc-link:hover {\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
||
|
|
" color: var(--sklearn-color-background);\n",
|
||
|
|
" text-decoration: none;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
|
||
|
|
".sk-estimator-doc-link.fitted:hover,\n",
|
||
|
|
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
|
||
|
|
".sk-estimator-doc-link.fitted:hover {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
||
|
|
" color: var(--sklearn-color-background);\n",
|
||
|
|
" text-decoration: none;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* Span, style for the box shown on hovering the info icon */\n",
|
||
|
|
".sk-estimator-doc-link span {\n",
|
||
|
|
" display: none;\n",
|
||
|
|
" z-index: 9999;\n",
|
||
|
|
" position: relative;\n",
|
||
|
|
" font-weight: normal;\n",
|
||
|
|
" right: .2ex;\n",
|
||
|
|
" padding: .5ex;\n",
|
||
|
|
" margin: .5ex;\n",
|
||
|
|
" width: min-content;\n",
|
||
|
|
" min-width: 20ex;\n",
|
||
|
|
" max-width: 50ex;\n",
|
||
|
|
" color: var(--sklearn-color-text);\n",
|
||
|
|
" box-shadow: 2pt 2pt 4pt #999;\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background: var(--sklearn-color-unfitted-level-0);\n",
|
||
|
|
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
".sk-estimator-doc-link.fitted span {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background: var(--sklearn-color-fitted-level-0);\n",
|
||
|
|
" border: var(--sklearn-color-fitted-level-3);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
".sk-estimator-doc-link:hover span {\n",
|
||
|
|
" display: block;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 a.estimator_doc_link {\n",
|
||
|
|
" float: right;\n",
|
||
|
|
" font-size: 1rem;\n",
|
||
|
|
" line-height: 1em;\n",
|
||
|
|
" font-family: monospace;\n",
|
||
|
|
" background-color: var(--sklearn-color-background);\n",
|
||
|
|
" border-radius: 1rem;\n",
|
||
|
|
" height: 1rem;\n",
|
||
|
|
" width: 1rem;\n",
|
||
|
|
" text-decoration: none;\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" color: var(--sklearn-color-unfitted-level-1);\n",
|
||
|
|
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
|
||
|
|
" color: var(--sklearn-color-fitted-level-1);\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"/* On hover */\n",
|
||
|
|
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
|
||
|
|
" /* unfitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-unfitted-level-3);\n",
|
||
|
|
" color: var(--sklearn-color-background);\n",
|
||
|
|
" text-decoration: none;\n",
|
||
|
|
"}\n",
|
||
|
|
"\n",
|
||
|
|
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
|
||
|
|
" /* fitted */\n",
|
||
|
|
" background-color: var(--sklearn-color-fitted-level-3);\n",
|
||
|
|
"}\n",
|
||
|
|
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier(max_depth=3, min_samples_leaf=10, random_state=1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> DecisionTreeClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.tree.DecisionTreeClassifier.html\">?<span>Documentation for DecisionTreeClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeClassifier(max_depth=3, min_samples_leaf=10, random_state=1)</pre></div> </div></div></div></div>"
|
||
|
|
],
|
||
|
|
"text/plain": [
|
||
|
|
"DecisionTreeClassifier(max_depth=3, min_samples_leaf=10, random_state=1)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 12,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.tree import DecisionTreeClassifier\n",
|
||
|
|
"\n",
|
||
|
|
"# Defining an object for DTC and fitting for whole dataset\n",
|
||
|
|
"dt = DecisionTreeClassifier(max_depth=3, min_samples_leaf=10, random_state=1 )\n",
|
||
|
|
"dt.fit(X, y)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 13,
|
||
|
|
"id": "9c6be7f6-ae65-4685-be32-5f945f53e869",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "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
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 640x480 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn import tree\n",
|
||
|
|
"\n",
|
||
|
|
"#print(dt.feature_names_in_)\n",
|
||
|
|
"\n",
|
||
|
|
"t = tree.plot_tree(decision_tree = dt, feature_names=dt.feature_names_in_) # returns a array with each leaf and their values"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 14,
|
||
|
|
"id": "80282a49-1d47-4146-afd8-a9aa359e9791",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"# Defining an object for DTC and fitting for train dataset\n",
|
||
|
|
"dt = DecisionTreeClassifier(random_state=1)\n",
|
||
|
|
"dt.fit(X_train, y_train)\n",
|
||
|
|
"\n",
|
||
|
|
"y_pred_train = dt.predict(X_train)\n",
|
||
|
|
"y_pred = dt.predict(X_test)\n",
|
||
|
|
"y_prob = dt.predict_proba(X_test)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 15,
|
||
|
|
"id": "af602439-ec2e-4ef7-88eb-6d3684fd70ee",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Accuracy of Decision Tree-Train: 1.0\n",
|
||
|
|
"Accuracy of Decision Tree-Test: 0.9545454545454546\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.metrics import accuracy_score\n",
|
||
|
|
"\n",
|
||
|
|
"print('Accuracy of Decision Tree-Train: ', accuracy_score(y_pred_train, y_train))\n",
|
||
|
|
"print('Accuracy of Decision Tree-Test: ', accuracy_score(y_pred, y_test))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 16,
|
||
|
|
"id": "0ae9915b-5145-4ffe-a49f-18d44064dfa5",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" precision recall f1-score support\n",
|
||
|
|
"\n",
|
||
|
|
" Iris-setosa 1.00 1.00 1.00 15\n",
|
||
|
|
"Iris-versicolor 1.00 0.87 0.93 15\n",
|
||
|
|
" Iris-virginica 0.88 1.00 0.93 14\n",
|
||
|
|
"\n",
|
||
|
|
" accuracy 0.95 44\n",
|
||
|
|
" macro avg 0.96 0.96 0.95 44\n",
|
||
|
|
" weighted avg 0.96 0.95 0.95 44\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.metrics import classification_report \n",
|
||
|
|
"#Classification for test before hyperparameter tuning\n",
|
||
|
|
"print(classification_report(y_test,y_pred))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 17,
|
||
|
|
"id": "6906db27-13f0-4e27-b08c-924a303e61ec",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"{'max_depth': 3, 'min_samples_leaf': 3, 'min_samples_split': 2}"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 17,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.model_selection import GridSearchCV\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"# Hyperparameter Tuning of DTC\n",
|
||
|
|
"\n",
|
||
|
|
"dt = DecisionTreeClassifier(random_state=1)\n",
|
||
|
|
"\n",
|
||
|
|
"params = {'max_depth' : [2,3,4,5],\n",
|
||
|
|
" 'min_samples_split': [2,3,4,5],\n",
|
||
|
|
" 'min_samples_leaf': [1,2,3,4,5]}\n",
|
||
|
|
"\n",
|
||
|
|
"gsearch = GridSearchCV(dt, param_grid=params, cv=3)\n",
|
||
|
|
"\n",
|
||
|
|
"gsearch.fit(X,y)\n",
|
||
|
|
"\n",
|
||
|
|
"gsearch.best_params_"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 18,
|
||
|
|
"id": "56a75b7b-2915-47e7-9f8b-1f12c72c2196",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"# Passing best parameter for the Hyperparameter Tuning\n",
|
||
|
|
"dt = DecisionTreeClassifier(**gsearch.best_params_, random_state=1)\n",
|
||
|
|
"\n",
|
||
|
|
"dt.fit(X_train, y_train)\n",
|
||
|
|
"\n",
|
||
|
|
"y_pred_train = dt.predict(X_train)\n",
|
||
|
|
"y_prob_train = dt.predict_proba(X_train)[:,1]\n",
|
||
|
|
"\n",
|
||
|
|
"y_pred = dt.predict(X_test)\n",
|
||
|
|
"y_prob = dt.predict_proba(X_test)[:,1]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 19,
|
||
|
|
"id": "59d0f61b-c0c7-4746-9706-2b0816dca073",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"text/plain": [
|
||
|
|
"[Text(0.4, 0.875, 'petal width (cm) <= 0.75\\ngini = 0.666\\nsamples = 102\\nvalue = [32, 34, 36]'),\n",
|
||
|
|
" Text(0.2, 0.625, 'gini = 0.0\\nsamples = 32\\nvalue = [32, 0, 0]'),\n",
|
||
|
|
" Text(0.6, 0.625, 'petal width (cm) <= 1.65\\ngini = 0.5\\nsamples = 70\\nvalue = [0, 34, 36]'),\n",
|
||
|
|
" Text(0.4, 0.375, 'petal length (cm) <= 4.95\\ngini = 0.149\\nsamples = 37\\nvalue = [0, 34, 3]'),\n",
|
||
|
|
" Text(0.2, 0.125, 'gini = 0.0\\nsamples = 33\\nvalue = [0, 33, 0]'),\n",
|
||
|
|
" Text(0.6, 0.125, 'gini = 0.375\\nsamples = 4\\nvalue = [0, 1, 3]'),\n",
|
||
|
|
" Text(0.8, 0.375, 'gini = 0.0\\nsamples = 33\\nvalue = [0, 0, 33]')]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"execution_count": 19,
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "execute_result"
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"data": {
|
||
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGFCAYAAABg2vAPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAACM20lEQVR4nOzdd1RU19oH4N8gMAwdRQVRKYI0W+SiIhhEFETFBDEWLIANVLAEo2IDsRcEewdELCREQ9AECyjWa0GwgcpVEL0BIxYiXZj9/eHHuY7S21DeZ61ZK7Nnl3cmc/Cdc87em8cYYyCEEEJIiyUh7gAIIYQQIl6UDBBCCCEtHCUDhBBCSAtHyQAhhBDSwlEyQAghhLRwlAwQQgghLRwlA4QQQkgLR8kAIYQQ0sJRMkAIIYS0cJQMEEIIIS0cJQOEEEJIC0fJACGEENLCUTJACCGEtHCUDBBCCCEtHCUDhBBCSAtHyQAhhBDSwlEyQAghhLRwkuIOgNROeno6srKyxB0GIWKjqqqKzp07izsMQpo0SgaasPT0dBgaGiIvL0/coRAiNrKyskhOTqaEgJBaoGSgCcvKykJeXh7CwsJgaGgo7nAIaXDJycmYOHEisrKyKBkgpBYoGWgGDA0N0bt3b3GHQQghpImiGwgJIYSQFo6SAUIIIaSFo2SAEEIIaeEoGSD1xtfXFwYGBnXWX0hICGRkZGpdBwC0tLSwfv36GsUxY8YMLF68uEZtqyo+Ph4dO3akmSKEkAZByQCplIyMDEJCQsQdBsaOHYvnz59Xq8369euhpaVVZzE8fPgQx48fx8KFC+usz7KYmJigd+/e8Pf3r9dxaiI7Oxuurq5QUVGBgoICfvjhB7x69arCNgMHDgSPx/vqYWxszNUJCQkps87Lly/r+y0R0uJRMkCaDIFAgPbt24s1hsDAQHz//fdo3bp1vY81depU7Ny5Ex8/fqxVP6mpqXUU0ScTJ07E9evXERUVhZiYGKSlpcHBwQGMsXLbnDhxAhkZGdwjLS0NCgoKGDNmjEg9Pp8vUi8jIwMdOnSo0/gJIV+jZKAZGzhwIKZPnw4vLy+0adMGSkpKmDlzJgoLC7k6jDFs2bIFenp6EAgEMDIywr59+7jXtbS0UFhYCFdXV+6XGgC8ffsWEyZMQKdOnSAQCKCvr4/AwMAK/0H40rhx4zBt2jTu+bp168Dj8RAdHc2VmZiYYO3atQDKvgSwadMmqKurQ05ODj/88APevXvHvRYSEgJvb288f/6ci93X15d7vbCwEDNnzoSSkhI6dOgAPz+/CuMtKSnBzz//jO+++06kvKioCEuXLoWWlhb4fD60tLS4mNPS0sDj8XD8+HFYW1tzn/G1a9eQmpoKa2tryMnJoUePHrh586ZIv3Z2dnj//j3Onz9fhU9TVFpaGlavXg19fX1MmTKl2u3L8/jxY5w6dQp79+6FhYUF+vTpg5CQEFy/fh1Xrlwpt13r1q2hpqbGPa5cuYLc3NwyY/u8npqaGiQk6M8UIfWOkSYrPj6eAWDx8fFlvm5packUFBSYm5sbS0pKYpGRkUxVVZUtXLiQq7N8+XLWpUsXFhUVxZ49e8Z++eUXpqKiwkJCQhhjjP3999+Mz+ezwMBAlpGRwTIyMhhjjL18+ZKtX7+excfHs2fPnrHQ0FAmEAhYWFgY17ePjw/T19cvN/49e/YwHR0d7rmNjY1IfO/evWMSEhLs2rVrjDHGgoODGZ/P5+r//PPPTFJSku3YsYM9fvyY+fv7M2VlZa5OXl4eW7p0KevYsSMX+4cPHxhjjGlqajJlZWW2adMm9uTJE7Zr1y4GgJ09e7bceO/cucMAsLS0NJHycePGMXV1dRYeHs6ePn3Krl69yvbv388YYyw1NZUBYF26dGGRkZHs8ePHbMSIEaxz587M0tKSK7O3t2e6urqspKREpO++ffuyxYsXlxvT57Kzs9mBAwfYt99+y3g8HuvXrx/bsWMHe/36NVfn0qVLTE5OrsKHm5tbuWMcPHiQycjIfBVnx44d2bp166oUJ2OfvpvDhw8XKQsODmY8Ho9paWmxDh06MFtbW3b16tUK+6nsGCCEVA0lA01YVZIBHR0dkT/cO3fuZAKBgBUWFrLc3FwmEAhYTEyMSDs/Pz9mYmLCPefz+Sw4OLjSeGbNmsVGjBjBPa8sGXj8+DEDwJ4/f86KioqYnJwc27BhAzM1NWWMMRYZGcnk5ORYUVERY+zrZMDMzIw5OzuL9PnDDz+I1Fm3bh3T1NT8amxNTU3m4OAgUmZsbFzhP7wnTpxgALh4GGPsyZMnDACLiooqs01pMrB9+3au7Nq1a+WWpaamirR3cHBg48aNKzemkpISdvr0aTZ27FgmIyPD9PT0mK+vL/vPf/5TZv28vDyWkpJS4ePVq1fljrdmzRrWqVOnr8r/9a9/sTlz5pTb7nOl/99/++03kfJr166x0NBQlpiYyK5cucKcnZ2ZpKQku3nzZrl9UTJASN2gFQibub59+4qcZjU3N0d+fj7S0tKQnZ2N/Px82Nvbc6f/AaC4uBh8Pr/CfoVCIfz9/XH06FG8ePECBQUFKCoqqtbsga5du0JDQwOxsbHo2rUrlJWVMX36dCxbtgzZ2dm4ePEiBgwYACkpqTLbJycnw8XFRaTM3Nwcv//+e5XG/+abb0Sea2hoVHgjXEFBAVq1aiUST0JCAgBg0KBBFY7Vs2dP7r/V1NTKLfv7779FbngUCATIzc0tt9/09HQMHz4cCgoK2LdvHyZNmlRhHAKBALq6uhXWqczn35WqlH9p//79UFdXx/Dhw0XKzczMYGZmxj03NzdHamoqNm/ejPDw8JoHTAipFF2Ma2HY/1/T5/F4EAqFAICTJ08iMTGRezx48ID7R648W7ZswZo1azBnzhycO3cOiYmJcHV1RVFRUbXiGThwIC5cuIALFy7AysoKKioq6NatGy5dusSV1eT9VcWXScbnn0lZ2rZti5KSEmRnZ3/VrjpjldYvq+zL8d++fYu2bduW22+nTp0QEREBKysrTJ06Faampti6dWu5Sc3ly5chLy9f4cPd3b3c8dTU1PD69euv4nz16hWX0FSkqKgIhw4dgqurKyQlK/8t0qdPHzx58qTSeoSQ2qEzA83czZs3IRQKubMD169fh0AggJaWFtTV1cHn85GamgobG5ty+5CWlkZJSYlIWVxcHIYPHw5XV1euLCUlpdrxWVlZYeXKlfjvf/8LJycnAJ8ShF9//RX37t0TuZnxS0ZGRvj3v/+NGTNmcGXXr1+vNPaa+uabb8Dj8fDgwQOYm5tzZYwxXLx4EcOGDauTcT53//59jBw5stzXW7VqBUdHRzg6OuLNmzc4duwYQkND4eXlBWtra0ycOBEODg6Ql5cHAPzrX/9CYmJihWMqKiqW+1r//v2Rn5+PK1eu4NtvvwXw6QzNixcvuM+kIr/99huysrIwderUSusCn868qKurV6kuIaTmKBlo5l69egVPT094enoiJSUFPj4+8PT0hJSUFKSkpLBw4UIsWrQIPB4PVlZWyM/PR3x8PLKysvDTTz8BALS1tXHhwgXY2dlBWloaqqqq0NfXx5EjRxAXFwd1dXUEBwcjPj6+2n+4raysMG3aNGRkZGD//v1c2ahRoyAvL1/hBkzz58+Hk5MTTE1NMXjwYJw+fRpnz54VqaOtrY3MzExcv34denp6kJWVhaysbDU/xU/atGkDU1NTxMXFcf/w6enpYfz48ZgxYwYCAwNhYmKCzMxMJCUlVfkfvPI8e/YMf/31F2xtbascn4eHBzw8PPDo0SMcPnwYy5YtQ0hICGJiYgDU/jKBgYEBhg8fDnd3d+zfvx/S0tKYPXs2zMzMYGFhwdWztrZGnz59sG7dOpH2+/btg7W1NXR0dL7qe+XKlejbty/09PSQk5OD/fv3IzY2FqdPn65xvISQqqHLBM3cuHHjICUlBTMzM0yYMAGjRo0SmULn5+eHtWvXYtu2bejWrRusrKwQHBws8sd68+bNuHPnDrS1tblT1suWLYOFhQXs7e3Rv39/5ObmYvbs2dWOT0dHB5qamtDQ0IC2tjY
|
||
|
|
"text/plain": [
|
||
|
|
"<Figure size 640x480 with 1 Axes>"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
"metadata": {},
|
||
|
|
"output_type": "display_data"
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"tree.plot_tree(decision_tree = dt, feature_names=dt.feature_names_in_)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 20,
|
||
|
|
"id": "eb0b0037-7305-4085-a668-92882fec7302",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"# Passing best parameter for the Hyperparameter Tuning\n",
|
||
|
|
"dt = DecisionTreeClassifier(**gsearch.best_params_, random_state=1)\n",
|
||
|
|
"\n",
|
||
|
|
"dt.fit(X_train, y_train)\n",
|
||
|
|
"\n",
|
||
|
|
"y_pred_train = dt.predict(X_train)\n",
|
||
|
|
"y_prob_train = dt.predict_proba(X_train)[:,1]\n",
|
||
|
|
"\n",
|
||
|
|
"y_pred = dt.predict(X_test)\n",
|
||
|
|
"y_prob = dt.predict_proba(X_test)[:,1]"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 21,
|
||
|
|
"id": "d191383c-ba55-43c8-97bb-88816b9763d4",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Confusion Matrix - Train: \n",
|
||
|
|
" [[32 0 0]\n",
|
||
|
|
" [ 0 33 1]\n",
|
||
|
|
" [ 0 0 36]]\n",
|
||
|
|
"\n",
|
||
|
|
" Confusion Matrix - Test: \n",
|
||
|
|
" [[15 0 0]\n",
|
||
|
|
" [ 0 13 2]\n",
|
||
|
|
" [ 0 0 14]]\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"from sklearn.metrics import confusion_matrix \n",
|
||
|
|
"\n",
|
||
|
|
"print('Confusion Matrix - Train:','\\n',confusion_matrix(y_train,y_pred_train))\n",
|
||
|
|
"print('\\n','Confusion Matrix - Test:','\\n',confusion_matrix(y_test,y_pred))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 22,
|
||
|
|
"id": "2e5cdce5-ada0-493e-aefa-e3415abb1d54",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
" precision recall f1-score support\n",
|
||
|
|
"\n",
|
||
|
|
" Iris-setosa 1.00 1.00 1.00 15\n",
|
||
|
|
"Iris-versicolor 1.00 0.87 0.93 15\n",
|
||
|
|
" Iris-virginica 0.88 1.00 0.93 14\n",
|
||
|
|
"\n",
|
||
|
|
" accuracy 0.95 44\n",
|
||
|
|
" macro avg 0.96 0.96 0.95 44\n",
|
||
|
|
" weighted avg 0.96 0.95 0.95 44\n",
|
||
|
|
"\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"#Classification for test after hyperparameter tuning\n",
|
||
|
|
"print(classification_report(y_test,y_pred))"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": 23,
|
||
|
|
"id": "55c4bb77-7646-4c0e-b2e2-24ae9e23e1db",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdout",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Accuracy of Decision Tree-Train: 0.9901960784313726\n",
|
||
|
|
"Accuracy of Decision Tree-Test: 0.9545454545454546\n"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"print('Accuracy of Decision Tree-Train: ', accuracy_score(y_pred_train, y_train))\n",
|
||
|
|
"print('Accuracy of Decision Tree-Test: ', accuracy_score(y_pred, y_test))"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"metadata": {
|
||
|
|
"kernelspec": {
|
||
|
|
"display_name": "Python 3 (ipykernel)",
|
||
|
|
"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": "3.11.7"
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"nbformat": 4,
|
||
|
|
"nbformat_minor": 5
|
||
|
|
}
|