intial commit (forked from private repo)

extracted_cells/cell18.py

@@ -0,0 +1,49 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+# Wählen wir zwei Features zur Variation:
+less_important_feature_education = "education.num"
+less_important_feature_fnlwgt = "fnlwgt" 
+
+# Festlegen derRange für die Variation der zwei Features
+education_range = np.linspace(instance_df[less_important_feature_education].values[0] - 10, instance_df[less_important_feature_education].values[0] + 10, 50)
+fnlwgt_range = np.linspace(instance_df[less_important_feature_fnlwgt].values[0] - 100000, instance_df[less_important_feature_fnlwgt].values[0] + 100000, 50)
+
+# Erstellen von Instanzen für LIME
+instances_education = pd.DataFrame([instance] * len(education_range), columns=X_train.columns)
+instances_fnlwgt = pd.DataFrame([instance] * len(fnlwgt_range), columns=X_train.columns)
+
+# Ändern der Feature-Werte in den Instanzen
+instances_education[less_important_feature_education] = education_range
+instances_fnlwgt[less_important_feature_fnlwgt] = fnlwgt_range
+
+# Vorhersagen mit dem Modell (Wahrscheinlichkeiten)
+instances_education["prediction"] = best_rf_model.predict_proba(instances_education)[:, 1]
+instances_fnlwgt["prediction"] = best_rf_model.predict_proba(instances_fnlwgt)[:, 1]
+
+# Bestimmen der y-Achsen-Grenzen (min/max für alle Vorhersagen)
+y_min = min(instances_education["prediction"].min(), instances_fnlwgt["prediction"].min())
+y_max = max(instances_education["prediction"].max(), instances_fnlwgt["prediction"].max())
+
+# Visualisierung der Variation von 'education-num' (moderater Einfluss)
+plt.figure(figsize=(8,5))
+plt.plot(education_range, instances_education["prediction"], label="Moderater Einfluss auf die Vorhersage", color='green')
+plt.axvline(instance_df[less_important_feature_education].values[0], color="red", linestyle="dashed", label="Originalwert")
+plt.xlabel("Bildungsniveau (education-num)")
+plt.ylabel("Vorhersage (0 = <=50K, 1 = >50K)")
+plt.title(f"Einfluss von {less_important_feature_education} auf die Vorhersage")
+plt.ylim([y_min, y_max])  # Einheitliche y-Achse
+plt.legend()
+plt.show()
+
+# Visualisierung der Variation von 'fnlwgt' (wenig Einfluss)
+plt.figure(figsize=(8,5))
+plt.plot(fnlwgt_range, instances_fnlwgt["prediction"], label="Wenig Einfluss auf die Vorhersage", color='orange')
+plt.axvline(instance_df[less_important_feature_fnlwgt].values[0], color="red", linestyle="dashed", label="Originalwert")
+plt.xlabel("Finales Gewicht (fnlwgt)")
+plt.ylabel("Vorhersage (0 = <=50K, 1 = >50K)")
+plt.title(f"Einfluss von {less_important_feature_fnlwgt} auf die Vorhersage")
+plt.ylim([y_min, y_max])  # Einheitliche y-Achse
+plt.legend()
+plt.show()