First upload with plot_decision_boundary function

Author: tirthajyoti

Utilities/ML-Python-utils.py

@@ -0,0 +1,58 @@
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+def plot_decision_boundaries(X, y, model_class, **model_params):
+    """Function to plot the decision boundaries of a classification model.
+    This uses just the first two columns of the data for fitting 
+    the model as we need to find the predicted value for every point in 
+    scatter plot.
+
+    Arguments:
+            X: Feature data as a NumPy-type array.
+            y: Label data as a NumPy-type array.
+            model_class: A Scikit-learn ML estimator class 
+            e.g. GaussianNB (imported from sklearn.naive_bayes) or
+            LogisticRegression (imported from sklearn.linear_model)
+            **model_params: Model parameters to be passed on to the ML estimator
+    
+    Typical code example:
+            plt.figure()
+            plt.title("KNN decision boundary with neighbros: 5",fontsize=16)
+            plot_decision_boundaries(X_train,y_train,KNeighborsClassifier,n_neighbors=5)
+            plt.show()
+    """
+    try:
+        X = np.array(X)
+        y = np.array(y).flatten()
+    except:
+        print("Coercing input data to NumPy arrays failed")
+    reduced_data = X[:, :2]
+    model = model_class(**model_params)
+    model.fit(reduced_data, y)
+
+    # Step size of the mesh. Decrease to increase the quality of the VQ.
+    h = .02     # point in the mesh [x_min, m_max]x[y_min, y_max].    
+
+    # Plot the decision boundary. For that, we will assign a color to each
+    x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
+    y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
+
+    # Obtain labels for each point in mesh using the model.
+    Z = model.predict(np.c_[xx.ravel(), yy.ravel()])    
+
+    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
+    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
+    xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1),
+                         np.arange(y_min, y_max, 0.1))
+
+    Z = model.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)
+
+    plt.contourf(xx, yy, Z, alpha=0.4)
+    plt.scatter(X[:, 0], X[:, 1], c=y, alpha=0.8)
+    plt.xlabel("Feature-1",fontsize=15)
+    plt.ylabel("Feature-2",fontsize=15)
+    plt.xticks(fontsize=14)
+    plt.yticks(fontsize=14)
+    return plt