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.pipeline import Pipeline
from sklearn.preprocessing import LabelEncoder, StandardScaler

# Load the CSV data
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 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)
    ])

pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(random_state=42))
])

# Train the model
pipeline.fit(X_train, y_train)

# Evaluate the model
accuracy = pipeline.score(X_test, y_test)
print('Accuracy:', accuracy)


# Create Flask app
app = Flask(__name__)

# Define API route for making predictions
@app.route('/predict', methods=['POST'])
def predict():
    # Get input data from request
    data = request.get_json()

    # Convert input data to dataframe
    input_data = pd.DataFrame(data, index=[0])

    # Make predictions using the trained pipeline
    predictions = pipeline.predict(input_data)

    # Prepare response
    response = {'prediction': predictions[0]}
    return jsonify(response)

# Run the Flask app
if __name__ == '__main__':
    app.run(debug=True)