From 84f965e255fbf72ca8a3027d34c2c6005b16b4ba Mon Sep 17 00:00:00 2001 From: Rushi-24 <2021.yeole.rushikesh@ves.ac.in> Date: Mon, 7 Oct 2024 20:51:30 +0530 Subject: [PATCH] Added feature importance of Age and Estimated salary via bar graph to Random Forest --- Code/Day 34 Random_Forest.md | 84 ++++++++++++++++-------------------- 1 file changed, 37 insertions(+), 47 deletions(-) diff --git a/Code/Day 34 Random_Forest.md b/Code/Day 34 Random_Forest.md index 7b55286..a24a8b7 100644 --- a/Code/Day 34 Random_Forest.md +++ b/Code/Day 34 Random_Forest.md @@ -1,85 +1,75 @@ -# Random Forests -

- -

- - -### Importing the libraries -```python +# Importing the libraries import numpy as np import matplotlib.pyplot as plt import pandas as pd -``` -### Importing the dataset -```python +# Importing the dataset dataset = pd.read_csv('Social_Network_Ads.csv') -X = dataset.iloc[:, [2, 3]].values -y = dataset.iloc[:, 4].values -``` -### Splitting the dataset into the Training set and Test set -```python -from sklearn.cross_validation import train_test_split -X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0) -``` +X = dataset.iloc[:, [2, 3]].values # Selecting Age and Estimated Salary columns +y = dataset.iloc[:, 4].values # Selecting the Purchased column + +# Splitting the dataset into the Training set and Test set +from sklearn.model_selection import train_test_split +X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0) -### Feature Scaling -```python +# Feature Scaling from sklearn.preprocessing import StandardScaler sc = StandardScaler() X_train = sc.fit_transform(X_train) X_test = sc.transform(X_test) -``` -### Fitting Random Forest to the Training set -```python + +# Fitting Random Forest to the Training set from sklearn.ensemble import RandomForestClassifier -classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0) +classifier = RandomForestClassifier(n_estimators=10, criterion='entropy', random_state=0) classifier.fit(X_train, y_train) -``` -### Predicting the Test set results -```python + +# Predicting the Test set results y_pred = classifier.predict(X_test) -``` -### Making the Confusion Matrix -```python + +# Making the Confusion Matrix from sklearn.metrics import confusion_matrix cm = confusion_matrix(y_test, y_pred) -``` -### Visualising the Training set results -```python + +# Visualising the Training set results from matplotlib.colors import ListedColormap X_set, y_set = X_train, y_train -X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01), - np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)) +X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.01), + np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.01)) plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), - alpha = 0.75, cmap = ListedColormap(('red', 'green'))) + alpha=0.75, cmap=ListedColormap(('red', 'green'))) plt.xlim(X1.min(), X1.max()) plt.ylim(X2.min(), X2.max()) for i, j in enumerate(np.unique(y_set)): plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], - c = ListedColormap(('red', 'green'))(i), label = j) + c=ListedColormap(('red', 'green'))(i), label=j) plt.title('Random Forest Classification (Training set)') plt.xlabel('Age') plt.ylabel('Estimated Salary') plt.legend() plt.show() -``` -### Visualising the Test set results -```python -from matplotlib.colors import ListedColormap + +# Visualising the Test set results X_set, y_set = X_test, y_test -X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01), - np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)) +X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.01), + np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.01)) plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), - alpha = 0.75, cmap = ListedColormap(('red', 'green'))) + alpha=0.75, cmap=ListedColormap(('red', 'green'))) plt.xlim(X1.min(), X1.max()) plt.ylim(X2.min(), X2.max()) for i, j in enumerate(np.unique(y_set)): plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1], - c = ListedColormap(('red', 'green'))(i), label = j) + c=ListedColormap(('red', 'green'))(i), label=j) plt.title('Random Forest Classification (Test set)') plt.xlabel('Age') plt.ylabel('Estimated Salary') plt.legend() plt.show() -``` + +# Visualizing Feature Importance +importances = classifier.feature_importances_ +features = ['Age', 'Estimated Salary'] # Naming the features +plt.figure(figsize=(8,6)) +plt.barh(features, importances, color='skyblue') +plt.xlabel('Importance') +plt.title('Feature Importance in Random Forest Model') +plt.show()