Add files via upload

Author: Janiishaan

salary_prediction.py

@@ -0,0 +1,86 @@
+# -*- coding: utf-8 -*-
+"""Salary-prediction.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1l22jFuwbNijASJOnbx3dE2q-8LSlvGaM
+"""
+
+!pip install pandas
+import pandas as pd
+
+# Load the datasets
+Placement_Train = pd.read_csv("/content/Placement_Test.csv")
+placement_test = pd.read_csv("/content/Placement_Train.csv")
+placement_sample_submission = pd.read_csv("/content/Plcement_Sample_Submission.csv")
+
+# Import necessary libraries
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestRegressor
+from sklearn.metrics import mean_squared_error
+from sklearn.preprocessing import LabelEncoder
+
+# Load the datasets
+placement_train = pd.read_csv("/content/Placement_Train.csv")
+placement_test = pd.read_csv("/content/Placement_Test.csv")
+placement_sample_submission = pd.read_csv("/content/Plcement_Sample_Submission.csv")
+
+# Display basic information about the training dataset
+print(placement_train.info())
+
+# Data Preprocessing
+# Encode categorical variables
+label_encoder = LabelEncoder()
+categorical_cols = ['gender', 'ssc_b', 'hsc_b', 'hsc_s', 'degree_t', 'workex', 'specialisation']
+for col in categorical_cols:
+    placement_train[col] = label_encoder.fit_transform(placement_train[col])
+    placement_test[col] = label_encoder.transform(placement_test[col])
+
+# Separate features and target variable
+X = placement_train.drop(['Annual_salary'], axis=1)
+y = placement_train['Annual_salary']
+
+# Split the data into training and testing sets
+X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# Build the model (Random Forest Regressor)
+model = RandomForestRegressor(n_estimators=100, random_state=42)
+model.fit(X_train, y_train)
+
+# Predict the annual salary on the validation set
+y_pred = model.predict(X_valid)
+
+# Evaluate the model
+mse = mean_squared_error(y_valid, y_pred)
+print(f'Mean Squared Error on Validation Set: {mse}')
+
+# Predict annual salary on the test set
+test_predictions = model.predict(placement_test)
+
+# Save predictions to a DataFrame
+submission = pd.DataFrame({'Annual_salary': test_predictions})
+
+# Save the submission DataFrame to a CSV file
+submission.to_csv('placement_submission.csv', index=False)
+
+# Predict annual salary on the test set
+test_predictions = model.predict(placement_test)
+
+# Create a DataFrame with SR_no and predicted Annual_salary
+results = pd.DataFrame({'SR_no': placement_test['SR_no'], 'Predicted_Annual_salary': test_predictions})
+
+# Display the results
+print(results)
+
+# Assuming 'results' is your DataFrame with SR_no and predicted Annual_salary
+results.to_csv('predicted_salary_results.csv', index=False)
+
+# Assuming 'results' is your DataFrame with SR_no and predicted Annual_salary
+results = results.rename(columns={'Predicted_Annual_salary': 'Annual_salary'})
+
+# Display the updated DataFrame
+print(results)
+
+results.to_csv('predicted_salary_results.csv', index=False)