# ------------------------------- Partial Dependency Plot-------------------------------- import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.ensemble import RandomForestRegressor import matplotlib.pyplot as plt from pdpbox import pdp, get_dataset, info_plots # Assuming 'data' is your DataFrame with the features and target variable. # Let's say 'target' is the column you want to predict and 'features' is the list of feature names. # Split the data into training and testing sets X_train, X_test, y_train, y_test = train_test_split(data[features], data[target], test_size=0.2, random_state=42) # Train a machine learning model (e.g., Random Forest Regressor) model = RandomForestRegressor() model.fit(X_train, y_train) # Create the PDP plot for a specific feature (e.g., 'feature_name') feature_to_plot = 'feature_name' pdp_dist = pdp.pdp_isolate(model=model, dataset=X_test, model_features=features, feature=feature_to_plot) # Plot the PDP pdp.pdp_plot(pdp_dist, feature_to_plot) plt.show()
Preview:
downloadDownload PNG
downloadDownload JPEG
downloadDownload SVG
Tip: You can change the style, width & colours of the snippet with the inspect tool before clicking Download!
Click to optimize width for Twitter