Update RandomForest/RandomForestClass.py

RandomForest/RandomForestClass.py

@@ -1,101 +1,101 @@
-import os
-import warnings
-import pandas as pd
-import numpy as np
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.metrics import accuracy_score, classification_report
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import MinMaxScaler
-import matplotlib.pyplot as plt
-import gradio as gr
-
-
-
-class My_RandomForest:
-    def __init__(self):
-        self.target_column = "Experience_Level"  # Change to suit your classification target
-        self.models = {
-            "Male": None,
-            "Female": None,
-            "Unspecified": None
-        }
-
-        # Default parameters
-        self.n_estimators = 10000  # Number of trees
-        self.max_depth = 4  # Maximum tree depth
-        self.max_features = 'sqrt'
-        self.criterion = 'gini'
-
-        self.accuracies = {"Male": None, "Female": None, "Unspecified": None}  # Store accuracies
-
-        self.selected_features = {
-            "Male": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"],
-            "Female": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"],
-            "Unspecified": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"]
-        }
-
-        self.scaler = MinMaxScaler()  # Initialize the scaler
-        self.init_dataset()
-
-    def init_dataset(self):
-        # Load the dataset
-        csv_file = os.path.join("app", "data", "gym_members_exercise_tracking.csv")
-        df_original = pd.read_csv(csv_file)
-        self.df_original = df_original
-
-    def train_model(self, gender="Unspecified"):
-        if gender not in self.models:
-            raise ValueError("Invalid gender specified. Choose from 'Male', 'Female', or 'Unspecified'.")
-
-        # Filter data by gender for training specific models
-        if gender == "Male":
-            df_filtered = self.df_original[self.df_original["Gender"] == "Male"]
-        elif gender == "Female":
-            df_filtered = self.df_original[self.df_original["Gender"] == "Female"]
-        else:
-            df_filtered = self.df_original  # Use all data for Unspecified
-
-        features = self.selected_features[gender]
-        X = df_filtered[features]
-        y = df_filtered[self.target_column]
-
-        # Split the data into training and testing sets
-        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-        # Fit the scaler on the training data and transform both sets
-        self.scaler.fit(X_train)
-        X_train = self.scaler.transform(X_train)
-        X_test = self.scaler.transform(X_test)
-
-        # Initialize and train the Random Forest model
-        model = RandomForestClassifier(
-            n_estimators=self.n_estimators,
-            max_depth=self.max_depth,
-            max_features=self.max_features,
-            criterion=self.criterion,
-            random_state=42
-        )
-        model.fit(X_train, y_train)
-
-        # Evaluate the model
-        y_pred = model.predict(X_test)
-        accuracy = accuracy_score(y_test, y_pred)
-
-        #print(f"{gender} Model Accuracy: {accuracy:.4f}")
-        #print(f"{gender} Model Classification Report:")
-        #print(classification_report(y_test, y_pred))
-
-        self.models[gender] = model
-        self.accuracies[gender] = accuracy  # Store the accuracy
-
-    def predict(self, input_data: pd.DataFrame, gender="Unspecified"):
-        if gender not in self.models or self.models[gender] is None:
-            raise ValueError(f"Model for {gender} is not trained yet.")
-
-        features = self.selected_features[gender]
-        scaled_input = self.scaler.transform(input_data[features])
-        prediction = self.models[gender].predict(scaled_input)
-        return prediction
-
-
-
+import os
+import warnings
+import pandas as pd
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score, classification_report
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MinMaxScaler
+import matplotlib.pyplot as plt
+import gradio as gr
+
+
+
+class My_RandomForest:
+    def __init__(self):
+        self.target_column = "Experience_Level"  # Change to suit your classification target
+        self.models = {
+            "Male": None,
+            "Female": None,
+            "Unspecified": None
+        }
+
+        # Default parameters
+        self.n_estimators = 10000  # Number of trees
+        self.max_depth = 4  # Maximum tree depth
+        self.max_features = 'sqrt'
+        self.criterion = 'gini'
+
+        self.accuracies = {"Male": None, "Female": None, "Unspecified": None}  # Store accuracies
+
+        self.selected_features = {
+            "Male": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"],
+            "Female": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"],
+            "Unspecified": ["Workout_Frequency (days/week)", "Session_Duration (hours)", "Water_Intake (liters)"]
+        }
+
+        self.scaler = MinMaxScaler()  # Initialize the scaler
+        self.init_dataset()
+
+    def init_dataset(self):
+        # Load the dataset
+        csv_file = os.path.join("data", "gym_members_exercise_tracking.csv")
+        df_original = pd.read_csv(csv_file)
+        self.df_original = df_original
+
+    def train_model(self, gender="Unspecified"):
+        if gender not in self.models:
+            raise ValueError("Invalid gender specified. Choose from 'Male', 'Female', or 'Unspecified'.")
+
+        # Filter data by gender for training specific models
+        if gender == "Male":
+            df_filtered = self.df_original[self.df_original["Gender"] == "Male"]
+        elif gender == "Female":
+            df_filtered = self.df_original[self.df_original["Gender"] == "Female"]
+        else:
+            df_filtered = self.df_original  # Use all data for Unspecified
+
+        features = self.selected_features[gender]
+        X = df_filtered[features]
+        y = df_filtered[self.target_column]
+
+        # Split the data into training and testing sets
+        X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+        # Fit the scaler on the training data and transform both sets
+        self.scaler.fit(X_train)
+        X_train = self.scaler.transform(X_train)
+        X_test = self.scaler.transform(X_test)
+
+        # Initialize and train the Random Forest model
+        model = RandomForestClassifier(
+            n_estimators=self.n_estimators,
+            max_depth=self.max_depth,
+            max_features=self.max_features,
+            criterion=self.criterion,
+            random_state=42
+        )
+        model.fit(X_train, y_train)
+
+        # Evaluate the model
+        y_pred = model.predict(X_test)
+        accuracy = accuracy_score(y_test, y_pred)
+
+        #print(f"{gender} Model Accuracy: {accuracy:.4f}")
+        #print(f"{gender} Model Classification Report:")
+        #print(classification_report(y_test, y_pred))
+
+        self.models[gender] = model
+        self.accuracies[gender] = accuracy  # Store the accuracy
+
+    def predict(self, input_data: pd.DataFrame, gender="Unspecified"):
+        if gender not in self.models or self.models[gender] is None:
+            raise ValueError(f"Model for {gender} is not trained yet.")
+
+        features = self.selected_features[gender]
+        scaled_input = self.scaler.transform(input_data[features])
+        prediction = self.models[gender].predict(scaled_input)
+        return prediction
+
+
+