Update app.py

app.py

@@ -1,95 +1,113 @@
-import numpy as np
-import pandas as pd
-from sklearn.model_selection import train_test_split
-from sklearn.ensemble import RandomForestRegressor
-import gradio as gr
-
-# Load dataset
-data = pd.read_csv('Life-Expectancy-Data-Updated.csv')
-
-# Define the feature columns and target column - 'Country' and 'Region' removed
-feature_cols = [
-    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality', 'Alcohol_consumption',
-    'Hepatitis_B', 'Measles', 'BMI', 'Polio', 'Diphtheria', 'Incidents_HIV', 'GDP_per_capita',
-    'Schooling', 'Economy_status_Developed', 'Economy_status_Developing'
-]
-target_col = 'Life_expectancy'
-X = data[feature_cols]
-y = data[target_col]
-
-# Split the data
-X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
-
-# Train the model
-rf_model = RandomForestRegressor(n_estimators=100, random_state=42)
-rf_model.fit(X_train, y_train)
-
-#-----------------------------------------------------------------------------------
-
-# Define the feature columns - must match the columns used in the training script
-feature_cols = [
-    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality', 'Alcohol_consumption',
-    'Hepatitis_B', 'Measles', 'BMI', 'Polio', 'Diphtheria', 'Incidents_HIV', 'GDP_per_capita',
-    'Schooling', 'Economy_status_Developed', 'Economy_status_Developing'
-]
-
-# Load the trained model
-#rf_model = joblib.load('rf_model.pkl')
-
-# Define the prediction function
-def predict_life_expectancy(
-    Infant_deaths, Under_five_deaths, Adult_mortality, Alcohol_consumption,
-    Hepatitis_B, Measles, BMI, Polio, Diphtheria, Incidents_HIV, GDP_per_capita,
-    Schooling, Economy_status
-):
-    # Initialize Economy_status features
-    Economy_status_Developed = 0
-    Economy_status_Developing = 0
-    
-    # Set the appropriate status to 1 based on the dropdown selection
-    if Economy_status == "Developed":
-        Economy_status_Developed = 1
-    else:  # economy_status == "Developing"
-        Economy_status_Developing = 1
-
-    # Convert the inputs to a DataFrame
-    input_data = pd.DataFrame([[
-        Infant_deaths, Under_five_deaths, Adult_mortality, Alcohol_consumption,
-        Hepatitis_B, Measles, BMI, Polio, Diphtheria, Incidents_HIV, GDP_per_capita,
-        Schooling, Economy_status_Developed, Economy_status_Developing
-    ]], columns=feature_cols)
-
-    # Make the prediction
-    prediction = rf_model.predict(input_data)[0]
-    return prediction
-
-# Create Gradio inputs for each feature
-inputs = [
-    #gr.Number(label=col) for col in feature_cols
-    gr.Slider(0, 1000, value=0, label="Infant_deaths",step=0.1),
-    gr.Slider(0, 1000, value=0, label="Under_five_deaths",step=0.1),
-    gr.Slider(0, 1000, value=0, label="Adult_mortality",step=0.1),
-    gr.Slider(0, 100, value=0, label="Alcohol_consumption",step=0.1),
-    gr.Slider(0, 100, value=99, label="Hepatitis_B", step=0.1),
-    gr.Slider(0, 100, value=99, label="Measles", step=0.1),
-    gr.Slider(0, 50, value=25, label="BMI", step=0.1),
-    gr.Slider(0, 100, value=99, label="Polio", step=0.1),
-    gr.Slider(0, 100, value=99, label="Diphtheria", step=0.1),
-    gr.Slider(0, 100, value=0, label="Incidents_HIV", step=0.1),
-    gr.Slider(0, 199999, value=0, label="GDP_per_capita", step=1),
-    gr.Slider(0, 100, value=0, label="Schooling", step=0.1),
-    gr.Dropdown(value=0, label="Economy Status", choices=["Developed", "Developing"])  # Dropdown for economy status
-]
-
-# Create the Gradio interface
-app = gr.Interface(
-    fn=predict_life_expectancy,    # Function to use for predictions
-    inputs=inputs,                 # The inputs for the model
-    outputs=gr.Textbox(label="Life Expectancy Prediction:"), # The output is a single number (life expectancy)
-    title="Life Expectancy Prediction",
-    description="Enter values for the features to predict life expectancy.",
-    theme=gr.themes.Base()
-)
-
-# Launch the Gradio app
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+import gradio as gr
+
+# Load dataset
+data = pd.read_csv('Life-Expectancy-Data-Updated.csv')
+
+# Define the feature columns and target column - 'Country' and 'Region' removed
+#feature_cols = [
+#    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality', 'Alcohol_consumption',
+#    'Hepatitis_B', 'Measles', 'BMI', 'Polio', 'Diphtheria', 'Incidents_HIV', 'GDP_per_capita',
+#    'Schooling', 'Economy_status_Developed', 'Economy_status_Developing'
+#]
+feature_cols = [ # Only 6 selected features used
+    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality',
+    'BMI', 'Polio', 'Schooling'
+]
+target_col = 'Life_expectancy'
+X = data[feature_cols]
+y = data[target_col]
+
+# Split the data
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Train the model
+#rf_model = RandomForestRegressor(n_estimators=100, random_state=42)
+# Based on CV tuning
+rf_model = RandomForestRegressor(max_depth=10, max_features='sqrt', min_samples_leaf=1, min_samples_split=2, n_estimators=200, random_state=42)
+rf_model.fit(X_train, y_train)
+
+#-----------------------------------------------------------------------------------
+
+# Define the feature columns - must match the columns used in the training script
+#feature_cols = [
+#    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality', 'Alcohol_consumption',
+#    'Hepatitis_B', 'Measles', 'BMI', 'Polio', 'Diphtheria', 'Incidents_HIV', 'GDP_per_capita',
+#    'Schooling', 'Economy_status_Developed', 'Economy_status_Developing'
+#]
+feature_cols = [ # Only 6 selected features used
+    'Infant_deaths', 'Under_five_deaths', 'Adult_mortality', 
+    'BMI', 'Polio', 'Schooling'
+]
+
+# Load the trained model
+#rf_model = joblib.load('rf_model.pkl')
+
+# Define the prediction function
+#def predict_life_expectancy(
+#    Infant_deaths, Under_five_deaths, Adult_mortality, Alcohol_consumption,
+#    Hepatitis_B, Measles, BMI, Polio, Diphtheria, Incidents_HIV, GDP_per_capita,
+#    Schooling, Economy_status
+#):
+def predict_life_expectancy(
+    Infant_deaths, Under_five_deaths, Adult_mortality,
+    BMI, Polio, Schooling
+):
+    # Initialize Economy_status features
+    #Economy_status_Developed = 0
+    #Economy_status_Developing = 0
+    
+    # Set the appropriate status to 1 based on the dropdown selection
+    #if Economy_status == "Developed":
+    #    Economy_status_Developed = 1
+    #else:  # economy_status == "Developing"
+    #    Economy_status_Developing = 1
+
+    # Convert the inputs to a DataFrame
+    #input_data = pd.DataFrame([[
+    #    Infant_deaths, Under_five_deaths, Adult_mortality, Alcohol_consumption,
+    #    Hepatitis_B, Measles, BMI, Polio, Diphtheria, Incidents_HIV, GDP_per_capita,
+    #    Schooling, Economy_status_Developed, Economy_status_Developing
+    #]], columns=feature_cols)
+    input_data = pd.DataFrame([[
+        Infant_deaths, Under_five_deaths, Adult_mortality,
+        BMI, Polio, Schooling
+    ]], columns=feature_cols)
+
+    # Make the prediction
+    prediction = rf_model.predict(input_data)[0]
+    return prediction
+
+# Create Gradio inputs for each feature
+inputs = [
+    #gr.Number(label=col) for col in feature_cols
+    gr.Slider(0, 1000, value=0, label="Infant_deaths",step=0.1),
+    gr.Slider(0, 1000, value=0, label="Under_five_deaths",step=0.1),
+    gr.Slider(0, 1000, value=0, label="Adult_mortality",step=0.1),
+    #gr.Slider(0, 100, value=0, label="Alcohol_consumption",step=0.1),
+    #gr.Slider(0, 100, value=99, label="Hepatitis_B", step=0.1),
+    #gr.Slider(0, 100, value=99, label="Measles", step=0.1),
+    gr.Slider(0, 50, value=25, label="BMI", step=0.1),
+    gr.Slider(0, 100, value=99, label="Polio", step=0.1),
+    #gr.Slider(0, 100, value=99, label="Diphtheria", step=0.1),
+    #gr.Slider(0, 100, value=0, label="Incidents_HIV", step=0.1),
+    #gr.Slider(0, 199999, value=0, label="GDP_per_capita", step=1),
+    gr.Slider(0, 100, value=0, label="Schooling", step=0.1),
+    #gr.Dropdown(value=0, label="Economy Status", choices=["Developed", "Developing"])  # Dropdown for economy status
+]
+
+# Create the Gradio interface
+app = gr.Interface(
+    fn=predict_life_expectancy,    # Function to use for predictions
+    inputs=inputs,                 # The inputs for the model
+    outputs=gr.Textbox(label="Life Expectancy Prediction:"), # The output is a single number (life expectancy)
+    title="Life Expectancy Prediction",
+    description="Enter values for the features to predict life expectancy.",
+    theme=gr.themes.Base()
+)
+
+# Launch the Gradio app
 app.launch()