File size: 2,880 Bytes
6ec2ef9 de0e3ad 6ec2ef9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 |
import pandas as pd
from scikit import sklearn
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
from streamlit import *
import joblib
# 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)
joblib.dump(pipeline, 'student_placement_model.joblib')
# Define Streamlit API
def predict_placement(internships, cgpa, history_of_backlogs, stream):
# Load the trained pipeline
pipeline = joblib.load('student_placement_model.joblib')
# Prepare input data
input_data = pd.DataFrame({'internships': [internships],
'cgpa': [cgpa],
'history_of_backlogs': [history_of_backlogs],
'stream': [stream]})
# Make prediction
prediction = pipeline.predict(input_data)
return prediction[0]
# Define Streamlit web app
def streamlit_app():
title('Student Placement Prediction')
internships = number_input('Number of internships:', min_value=0, max_value=10, step=1)
cgpa = number_input('CGPA:', min_value=0.0, max_value=10.0, step=0.1)
history_of_backlogs = number_input('Number of history of backlogs:', min_value=0, max_value=10, step=1)
stream = selectbox('Stream:', options=['Science', 'Commerce', 'Arts'])
prediction = predict_placement(internships, cgpa, history_of_backlogs, stream)
if prediction == 1:
result = 'Placed'
else:
result = 'Not Placed'
button('Predict Placement')
write(f'Result: {result}')
if __name__ == '__main__':
streamlit_app()
|