Add files via upload

Author: Tharuniiii

Salary_Data.csv

@@ -0,0 +1,31 @@
+YearsExperience,Salary
+1.1,39343
+1.3,46205
+1.5,37731
+2,43525
+2.2,39891
+2.9,56642
+3,60150
+3.2,54445
+3.2,64445
+3.7,57189
+3.9,63218
+4,55794
+4,56957
+4.1,57081
+4.5,61111
+4.9,67938
+5.1,66029
+5.3,83088
+5.9,81363
+6,93940
+6.8,91738
+7.1,98273
+7.9,101302
+8.2,113812
+8.7,109431
+9,105582
+9.5,116969
+9.6,112635
+10.3,122391
+10.5,121872

app.py

@@ -0,0 +1,27 @@
+import streamlit as st
+import pickle
+import numpy as np
+
+# Load the saved model
+model = pickle.load(open(r"C:\Users\Tharuni\Desktop\NIT\Aug month\18th-regression frontned backedn\linear_regression_model.pkl", 'rb'))
+
+# Set the title of the Streamlit app
+st.title("Salary Prediction App ")
+
+# Add a brief description
+st.write("This app predicts the salary based on years of experience using a simple linear regression model.")
+
+# Add input widget for user to enter years of experience
+years_experience = st.number_input("Enter Years of Experience:", min_value=0.0, max_value=50.0, value=1.0, step=0.5)
+
+# When the button is clicked, make predictions
+if st.button("Predict Salary"):
+ # Make a prediction using the trained model
+ experience_input = np.array([[years_experience]]) # Convert the input to a 2D array for prediction
+ prediction = model.predict(experience_input)
+ 
+ # Display the result
+ st.success(f"The predicted salary for {years_experience} years of experience is: ${prediction[0]:,.2f}")
+ 
+# Display information about the model
+st.write("The model was trained using a dataset of salaries and years of experience.built model by prakash senapati")

linear_regression_model.pkl

@@ -0,0 +1,66 @@
+import numpy as np 
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+from sklearn.metrics import mean_squared_error
+import os
+import pickle
+
+# Load the dataset
+dataset = pd.read_csv(r"C:\Users\Tharuni\Desktop\NIT\Aug month\18th-regression frontned backedn\Salary_Data.csv")
+# Split the data into independent and dependent variables
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 1].values 
+
+# Split the dataset into training and testing sets (80-20%)
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=0)
+
+# Train the model
+regressor = LinearRegression()
+regressor.fit(X_train, y_train)
+
+# Predict the test set
+y_pred = regressor.predict(X_test)
+
+# Visualize the training set
+plt.scatter(X_train, y_train, color='red') 
+plt.plot(X_train, regressor.predict(X_train), color='blue')
+plt.title('Salary vs Experience (Training set)')
+plt.xlabel('Years of Experience')
+plt.ylabel('Salary')
+plt.show()
+
+# Visualize the test set
+plt.scatter(X_test, y_test, color='red') 
+plt.plot(X_train, regressor.predict(X_train), color='blue')
+plt.title('Salary vs Experience (Test set)')
+plt.xlabel('Years of Experience')
+plt.ylabel('Salary')
+plt.show()
+
+# Predict salary for 12 and 20 years of experience using the trained model
+y_12 = regressor.predict([[12]])
+y_20 = regressor.predict([[20]])
+print(f"Predicted salary for 12 years of experience: ${y_12[0]:,.2f}")
+print(f"Predicted salary for 20 years of experience: ${y_20[0]:,.2f}")
+
+# Check model performance
+bias = regressor.score(X_train, y_train)
+variance = regressor.score(X_test, y_test)
+train_mse = mean_squared_error(y_train, regressor.predict(X_train))
+test_mse = mean_squared_error(y_test, y_pred)
+
+print(f"Training Score (R^2): {bias:.2f}")
+print(f"Testing Score (R^2): {variance:.2f}")
+print(f"Training MSE: {train_mse:.2f}")
+print(f"Test MSE: {test_mse:.2f}")
+
+# Save the trained model to disk
+filename = 'linear_regression_model.pkl'
+with open(filename, 'wb') as file:
+ pickle.dump(regressor, file)
+print("Model has been pickled and saved as linear_regression_model.pkl")
+
+print("Full path:", os.path.abspath(filename))
+

regression.py

@@ -0,0 +1,56 @@
+# Import necessary libraries
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.linear_model import LinearRegression
+
+# Load the dataset
+dataset = pd.read_csv(r"C:\Users\Tharuni\Desktop\NIT\Aug month\18th-regression frontned backedn\Salary_Data.csv")
+
+# Check the shape of the dataset
+print("Dataset Shape:", dataset.shape) # (30, 2)
+
+# Feature selection (independent variable X and dependent variable y)
+x = dataset.iloc[:, :-1] # Years of experience (Independent variable)
+y = dataset.iloc[:, -1] # Salary (Dependent variable)
+
+# Split the dataset into training and testing sets (80% training, 20% testing)
+
+x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.20, random_state=0)
+
+# Reshape x_train and x_test into 2D arrays if they are single feature columns
+x_train = x_train.values.reshape(-1, 1)
+x_test = x_test.values.reshape(-1, 1)
+
+# You don't need to reshape y_train, as it's the target variable
+# Fit the Linear Regression model to the training set
+regressor = LinearRegression()
+regressor.fit(x_train, y_train)
+
+# Predicting the results for the test set
+y_pred = regressor.predict(x_test)
+
+# Visualizing the Training set results
+plt.scatter(x_train, y_train, color = 'red') # Real salary data (training)
+plt.plot(x_train, regressor.predict(x_train), color = 'blue') # Predicted regression line
+plt.title('Salary vs Experience (Training set)')
+plt.xlabel('Years of Experience')
+plt.ylabel('Salary')
+plt.show()
+
+# Visualizing the Test set results
+plt.scatter(x_test, y_test, color = 'red') # Real salary data (testing)
+plt.plot(x_train, regressor.predict(x_train), color = 'blue') # Regression line from training set
+plt.title('Salary vs Experience (Test set)')
+plt.xlabel('Years of Experience')
+plt.ylabel('Salary')
+plt.show()
+
+# Optional: Output the coefficients of the linear model
+print(f"Intercept: {regressor.intercept_}")
+print(f"Coefficient: {regressor.coef_}")
+
+# Compare predicted and actual salaries from the test set
+comparison = pd.DataFrame({'Actual': y_test, 'Predicted': y_pred})
+print(comparison)