From 6286767e4ac6cf07d00f8a72c71b825e55031720 Mon Sep 17 00:00:00 2001 From: Arun Kumar Pandey Date: Thu, 7 Mar 2024 21:35:22 +0100 Subject: [PATCH] Here I discussed the ASM for the decision tree --- .../Project-2.4-Decision-tree.ipynb | 244 ++++++++++++++++++ 1 file changed, 244 insertions(+) create mode 100644 Supervised-learning/Project-2.4-Decision-tree.ipynb diff --git a/Supervised-learning/Project-2.4-Decision-tree.ipynb b/Supervised-learning/Project-2.4-Decision-tree.ipynb new file mode 100644 index 0000000..a4af255 --- /dev/null +++ b/Supervised-learning/Project-2.4-Decision-tree.ipynb @@ -0,0 +1,244 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Decision Tree" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + " User ID Gender Age EstimatedSalary Purchased\n", + "0 15624510 Male 19 19000 0\n", + "1 15810944 Male 35 20000 0\n", + "2 15668575 Female 26 43000 0\n", + "3 15603246 Female 27 57000 0\n", + "4 15804002 Male 19 76000 0\n" + ] + } + ], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "import random \n", + "import matplotlib.pyplot as plt \n", + "\n", + "df_user = pd.read_csv('User_Data.csv')\n", + "\n", + "# Display the DataFrame\n", + "print(df_user.head())" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [], + "source": [ + "# Importing the dataset \n", + "X = df_user.iloc[:, [2, 3]].values \n", + "y = df_user.iloc[:, 4].values " + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "# Splitting the dataset into the Training set and Test set \n", + "from sklearn.model_selection import train_test_split \n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [], + "source": [ + "# Feature Scaling \n", + "from sklearn.preprocessing import StandardScaler \n", + "sc = StandardScaler() \n", + "X_train = sc.fit_transform(X_train) \n", + "X_test = sc.transform(X_test) " + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
DecisionTreeClassifier(criterion='entropy', random_state=0)
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + ], + "text/plain": [ + "DecisionTreeClassifier(criterion='entropy', random_state=0)" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "#Fitting Decision Tree classifier to the training set \n", + "\n", + "from sklearn.tree import DecisionTreeClassifier\n", + "\n", + "classifier = DecisionTreeClassifier(criterion='entropy', random_state=0)\n", + "classifier.fit(X_train, y_train)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In the above code, we have created a classifier object, in which we have passed two main parameters;\n", + "\n", + "- `criterion='entropy'`: Criterion is used to measure the quality of split, which is calculated by information gain given by entropy.\n", + "- `random_state=0\"`: For generating the random states." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "#Predicting the test set result \n", + "y_pred= classifier.predict(X_test) " + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": {}, + "outputs": [], + "source": [ + "#Creating the Confusion matrix \n", + "from sklearn.metrics import confusion_matrix \n", + "cm= confusion_matrix(y_test, y_pred) " + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "C:\\Users\\hp\\AppData\\Local\\Temp\\ipykernel_18076\\1231252719.py:18: UserWarning: *c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2D array with a single row if you intend to specify the same RGB or RGBA value for all points.\n", + " axes[0].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],\n", + "C:\\Users\\hp\\AppData\\Local\\Temp\\ipykernel_18076\\1231252719.py:36: UserWarning: *c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*. Please use the *color* keyword-argument or provide a 2D array with a single row if you intend to specify the same RGB or RGBA value for all points.\n", + " axes[1].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],\n" + ] + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Importing libraries\n", + "import matplotlib.pyplot as plt\n", + "from matplotlib.colors import ListedColormap\n", + "\n", + "# Set up the figure with two subplots in one row and two columns\n", + "fig, axes = plt.subplots(1, 2, figsize=(12, 6))\n", + "\n", + "# Visulaizing the training set result\n", + "x_set, y_set = X_train, y_train\n", + "X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),\n", + " np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))\n", + "axes[0].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n", + " alpha=0.75, cmap=ListedColormap(['#87CEEB', '#90EE90']))\n", + "axes[0].set_xlim(X1.min(), X1.max())\n", + "axes[0].set_ylim(X2.min(), X2.max())\n", + "\n", + "for i, j in enumerate(np.unique(y_set)):\n", + " axes[0].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],\n", + " c=ListedColormap(['#0000FF', '#2ca02c'])(i), label=j)\n", + "\n", + "axes[0].set_title('K-NN Algorithm (Training set)')\n", + "axes[0].set_xlabel('Age')\n", + "axes[0].set_ylabel('Estimated Salary')\n", + "axes[0].legend()\n", + "\n", + "# Visulaizing the test set result\n", + "x_set, y_set = X_test, y_test\n", + "X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),\n", + " np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))\n", + "axes[1].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),\n", + " alpha=0.75, cmap=ListedColormap(['#87CEEB', '#90EE90']))\n", + "axes[1].set_xlim(X1.min(), X1.max())\n", + "axes[1].set_ylim(X2.min(), X2.max())\n", + "\n", + "for i, j in enumerate(np.unique(y_set)):\n", + " axes[1].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],\n", + " c=ListedColormap(['#0000FF', '#2ca02c'])(i), label=j)\n", + "\n", + "axes[1].set_title('K-NN Algorithm (Test set)')\n", + "axes[1].set_xlabel('Age')\n", + "axes[1].set_ylabel('Estimated Salary')\n", + "axes[1].legend()\n", + "\n", + "plt.tight_layout()\n", + "plt.show()\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "As we can see in the above image that there are some green data points within the purple region and vice versa. So, these are the incorrect predictions which we have discussed in the confusion matrix." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.12.0" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}