Update my_pages/multiverse.py

my_pages/multiverse.py

@@ -8,27 +8,31 @@ import pandas as pd
 import numpy as np
 
 from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import MinMaxScaler, StandardScaler
+from sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler
 from sklearn.neural_network import MLPClassifier
 from sklearn.linear_model import SGDClassifier
 from sklearn.ensemble import RandomForestClassifier
+from sklearn.tree import DecisionTreeClassifier
 from sklearn.preprocessing import LabelEncoder
+from sklearn.feature_selection import SelectKBest, f_classif
+from sklearn.decomposition import PCA
 
 choices_list = [
     {"label": "Data Scaling", "options": [
         "MinMax Scaler",
-        "Standard Scaler"
+        "Standard Scaler",
+        "Robust Scaler"
+    ]},
+    {"label": "Feature Selection", "options": [
+        "Select K Best (k=5)",
+        "PCA (n=5)",
+        "All Features"
     ]},
     {"label": "Model Architecture", "options": [
         "Logistic Regression",
-        "Random Forest",
+        "Decision Tree",
         "Neural Network (Small)"
     ]},
-    {"label": "Training Iterations", "options": [
-        "200",
-        "500",
-        "1000"
-    ]},
     {"label": "Random Seed", "options": [
         "1", "2", "3", "4", "5", "6", "7", "8", "9", "10"
     ]}
@@ -217,17 +221,22 @@ def render():
     ##########################
 
 
-    def split_and_scale(features, label, test_split=0.2, preprocess_scale=True):
+    def split_and_scale(features, label, test_split=0.2, preprocess_scale=None):
         X_train, X_test, y_train, y_test = train_test_split(features, label, test_size=test_split, random_state=0)
     
-        if preprocess_scale:
-            scaler = MinMaxScaler()
+        if preprocess_scale is not None:
+            if preprocess_scale=="MinMax Scaler":
+                scaler = MinMaxScaler()
+            elif preprocess_scale=="Standard Scaler":
+                scaler = StandardScaler()
+            elif preprocess_scale=="Robust Scaler":
+                scaler = RobustScaler()
             scaler.fit(X_train)
             X_train, X_test = scaler.transform(X_train), scaler.transform(X_test)
     
         return X_train, X_test, y_train, y_test
     
-    def get_stackoverflow_dataset(test_split=0.2, preprocess_scale=True):
+    def get_stackoverflow_dataset(test_split=0.2, preprocess_scale=None):
         data = pd.read_csv('loan_approval_dataset.csv')
 
         features = data.drop(columns=["loan_id", " loan_status"])
@@ -242,15 +251,22 @@ def render():
     
     
     ### Main Code Starts Here
-    scaler, arch, iterations, seed = selected_path[0], selected_path[1], int(selected_path[2]), int(selected_path[3])
-    random_seed = seed
-        
-    X_train, X_test, y_train, y_test = get_stackoverflow_dataset()
+    scaler, feature_sel, arch, seed = selected_path[0], selected_path[1], selected_path[2], int(selected_path[3])
+    X_train, X_test, y_train, y_test = get_stackoverflow_dataset(preprocess_scale=scaler)
+
+    if feature_sel=="Select K Best (k=5)":
+        selector = SelectKBest(score_func=f_classif, k=5)
+        X_train = selector.fit_transform(X_train, y_train)
+        X_test = selector.transform(X_test)
+    elif feature_sel=="PCA (n=5)":
+        pca = PCA(n_components=2)
+        X_train = pca.fit_transform(X_train, y_train)
+        X_test = pca.transform(X_test)
     
     placeholder = st.empty()
-    modelclass_dict = {'Neural Network (Small)': MLPClassifier([10], random_state=random_seed, max_iter=iterations),
-                       'Logistic Regression': SGDClassifier(random_state=random_seed, max_iter=iterations),
-                       'Random Forest': RandomForestClassifier(random_state=random_seed)}
+    modelclass_dict = {'Neural Network (Small)': MLPClassifier([10], random_state=seed, max_iter=iterations),
+                       'Logistic Regression': SGDClassifier(random_state=seed, max_iter=iterations),
+                       'Decision Tree': DecisionTreeClassifier(random_state=seed)}
     model = modelclass_dict[arch]
     placeholder.write("Training your model.")
     model.fit(X_train, y_train)