Update app.py

app.py

@@ -1,54 +1,39 @@
+# Import necessary libraries
 import pandas as pd
-from flask import Flask, request, jsonify
-
-from sklearn.compose import ColumnTransformer
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.impute import SimpleImputer
 from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score
 from sklearn.pipeline import Pipeline
-from sklearn.preprocessing import LabelEncoder, StandardScaler
-from streamlit import *
-import joblib
-
+from sklearn.preprocessing import StandardScaler
+import gradio as gr
 
-# Load the CSV data
+# Load the CSV data into a pandas DataFrame
 data = pd.read_csv('dataset.csv')
 
-# Split the data into features and labels
-X = data.drop('PlacedOrNot', axis=1)
-y = data['PlacedOrNot']
-
-# Encode categorical features
-categorical_features = ['HistoryOfBacklogs']
-for feature in categorical_features:
-    encoder = LabelEncoder()
-    X[feature] = encoder.fit_transform(X[feature])
+# Split the data into features (X) and labels (y)
+X = data.iloc[:, :-1]  # All columns except the last one
+y = data.iloc[:, -1]  # Last column (placed or not)
 
 # 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)
 
-# Create the pipeline
-numerical_features = ['Internships', 'CGPA']
-numerical_transformer = StandardScaler()
-categorical_features = [ 'HistoryOfBacklogs']
-categorical_transformer = SimpleImputer(strategy='most_frequent')
-preprocessor = ColumnTransformer(
-    transformers=[
-        ('num', numerical_transformer, numerical_features),
-        ('cat', categorical_transformer, categorical_features)
-    ])
-
+# Create a pipeline with a Random Forest Classifier
 pipeline = Pipeline([
-    ('preprocessor', preprocessor),
-    ('classifier', RandomForestClassifier(random_state=42))
+    ('scaler', StandardScaler()),  # Standardize features
+    ('classifier', RandomForestClassifier())  # Random Forest Classifier
 ])
 
-# Train the model
+# Fit the pipeline to the training data
 pipeline.fit(X_train, y_train)
 
-# Evaluate the model
-accuracy = pipeline.score(X_test, y_test)
+# Make predictions on the testing data
+y_pred = pipeline.predict(X_test)
+
+# Calculate accuracy of the model
+accuracy = accuracy_score(y_test, y_pred)
 print('Accuracy:', accuracy)
+
+# Define the input and output types for Gradio
 input_type = 'csv'
 output_type = 'label'
 
@@ -71,4 +56,4 @@ iface = gr.Interface(fn=predict_placement,
                      description='Predicts whether a student will be placed in a job or not based on internships, CGPA, and history of backlogs.')
 
 # Launch the Gradio interface
-iface.launch()
+iface.launch()