import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.metrics import accuracy_score
import streamlit as st

# Load the CSV data
data = pd.read_csv('dataset.csv')


# Split the data into features and target variable
X = data.drop('PlacedOrNot', axis=1)
y = data['PlacedOrNot']

# 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)


# 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)

preprocessor = ColumnTransformer(
    transformers=[
        ('num', StandardScaler(), ['internships', 'cgpa', 'history_of_backlogs']),
        ('cat', OneHotEncoder(), ['gender', 'stream'])
    ])

# Create the pipeline with Random Forest classifier
pipeline = Pipeline([
    ('preprocessor', preprocessor),
    ('classifier', RandomForestClassifier(random_state=42))
])

# Fit the pipeline to the training data
pipeline.fit(X_train, y_train)

# Make predictions on the test data
y_pred = pipeline.predict(X_test)

# Calculate accuracy of the model
accuracy = accuracy_score(y_test, y_pred)
print('Accuracy:', accuracy)

joblib.dump(pipeline, 'student_placement_model.joblib')

# Define Streamlit API
# Streamlit API for serving the model
st.title('Student Job Placement Prediction')

# Input form for user to enter features
st.markdown('Please enter the following information:')
internships = st.number_input('Number of Internships', min_value=0, max_value=10)
cgpa = st.number_input('CGPA', min_value=0.0, max_value=10.0)
history_of_backlogs = st.number_input('History of Backlogs', min_value=0, max_value=10)
gender = st.selectbox('Gender', ('Male', 'Female'))
stream = st.selectbox('Stream', ('Engineering', 'Science', 'Commerce'))
submit = st.button('Submit')

# Make prediction on user input when 'Submit' button is clicked
if submit:
    # Create a dataframe with user input
    user_data = pd.DataFrame([[internships, cgpa, history_of_backlogs, gender, stream]],
                             columns=['internships', 'cgpa', 'history_of_backlogs', 'gender', 'stream'])
    # Make prediction using the pipeline
    prediction = pipeline.predict(user_data)
    # Display prediction
    if prediction[0] == 1:
        st.success('Congratulations! The student is likely to be placed.')
    else:
        st.warning('Sorry, the student is unlikely to be placed.')