Add Project (Issue #16)

predicting-salary-using-sk-learn-linear-regression.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":608978,"sourceType":"datasetVersion","datasetId":297188}],"dockerImageVersionId":30775,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"raw","source":"# **Using Linear Regression Model to Predict salary.**","metadata":{}},{"cell_type":"markdown","source":"## ****Importing Libraries****","metadata":{}},{"cell_type":"code","source":"#Importing Libraries for Dataset and Visualization\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\n#Importing Machine Learning Libraries\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import r2_score,mean_squared_error","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-09-30T17:45:20.540618Z","iopub.execute_input":"2024-09-30T17:45:20.541077Z","iopub.status.idle":"2024-09-30T17:45:22.090891Z","shell.execute_reply.started":"2024-09-30T17:45:20.541034Z","shell.execute_reply":"2024-09-30T17:45:22.089678Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## **Reading CSV**","metadata":{}},{"cell_type":"code","source":"#Reading CSV\ndf = pd.read_csv(\"/kaggle/input/random-salary-data-of-employes-age-wise/Salary_Data.csv\")\ndf.head()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.092985Z","iopub.execute_input":"2024-09-30T17:45:22.093501Z","iopub.status.idle":"2024-09-30T17:45:22.170002Z","shell.execute_reply.started":"2024-09-30T17:45:22.093460Z","shell.execute_reply":"2024-09-30T17:45:22.168661Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## **Performing EDA**","metadata":{}},{"cell_type":"code","source":"#Data Description\ndf.describe()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.171391Z","iopub.execute_input":"2024-09-30T17:45:22.171781Z","iopub.status.idle":"2024-09-30T17:45:22.194179Z","shell.execute_reply.started":"2024-09-30T17:45:22.171741Z","shell.execute_reply":"2024-09-30T17:45:22.192901Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Data Information\ndf.info()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.197171Z","iopub.execute_input":"2024-09-30T17:45:22.197770Z","iopub.status.idle":"2024-09-30T17:45:22.218637Z","shell.execute_reply.started":"2024-09-30T17:45:22.197715Z","shell.execute_reply":"2024-09-30T17:45:22.217370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Checking Nulls\ndf.isna().sum()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.220223Z","iopub.execute_input":"2024-09-30T17:45:22.221062Z","iopub.status.idle":"2024-09-30T17:45:22.231880Z","shell.execute_reply.started":"2024-09-30T17:45:22.221005Z","shell.execute_reply":"2024-09-30T17:45:22.230710Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Checking Duplicates\ndf.duplicated().sum()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.233755Z","iopub.execute_input":"2024-09-30T17:45:22.234837Z","iopub.status.idle":"2024-09-30T17:45:22.244112Z","shell.execute_reply.started":"2024-09-30T17:45:22.234780Z","shell.execute_reply":"2024-09-30T17:45:22.243001Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Plotting Data points\nplt.figure(figsize =(10, 6))\nplt.scatter(df['YearsExperience'], df['Salary'])\n\n#Adding Labels\nplt.xlabel(\"Years of Experience\")\nplt.ylabel(\"Salary\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.245725Z","iopub.execute_input":"2024-09-30T17:45:22.246245Z","iopub.status.idle":"2024-09-30T17:45:22.547379Z","shell.execute_reply.started":"2024-09-30T17:45:22.246193Z","shell.execute_reply":"2024-09-30T17:45:22.546321Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Checking Outliers\nsns.boxplot(df['YearsExperience'])\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.548878Z","iopub.execute_input":"2024-09-30T17:45:22.549237Z","iopub.status.idle":"2024-09-30T17:45:22.685731Z","shell.execute_reply.started":"2024-09-30T17:45:22.549199Z","shell.execute_reply":"2024-09-30T17:45:22.684651Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## **Applying Linear Regression** ","metadata":{}},{"cell_type":"code","source":"#Preparing Data\nX = df['YearsExperience'].values.reshape(-1,1)\ny = df['Salary'].values.reshape(-1,1)","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.689636Z","iopub.execute_input":"2024-09-30T17:45:22.690062Z","iopub.status.idle":"2024-09-30T17:45:22.696843Z","shell.execute_reply.started":"2024-09-30T17:45:22.690022Z","shell.execute_reply":"2024-09-30T17:45:22.695405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Spliting Data for Train and Test\nX_train, X_test, y_train, y_test = train_test_split(X , y, test_size = 0.2, random_state = 42)","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.699014Z","iopub.execute_input":"2024-09-30T17:45:22.699478Z","iopub.status.idle":"2024-09-30T17:45:22.708301Z","shell.execute_reply.started":"2024-09-30T17:45:22.699424Z","shell.execute_reply":"2024-09-30T17:45:22.706949Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Applying Linear Regression\nlr = LinearRegression()\nlr.fit(X_train, y_train)","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.710816Z","iopub.execute_input":"2024-09-30T17:45:22.711300Z","iopub.status.idle":"2024-09-30T17:45:22.737890Z","shell.execute_reply.started":"2024-09-30T17:45:22.711244Z","shell.execute_reply":"2024-09-30T17:45:22.736790Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_hat = lr.predict(X_test)\ny_hat","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.740419Z","iopub.execute_input":"2024-09-30T17:45:22.741195Z","iopub.status.idle":"2024-09-30T17:45:22.750063Z","shell.execute_reply.started":"2024-09-30T17:45:22.741142Z","shell.execute_reply":"2024-09-30T17:45:22.748979Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize= (10, 6))\nplt.scatter(X_train, y_train, color = \"b\")\nplt.plot(X_train, lr.predict(X_train), c = \"orange\")\nplt.xlabel(\"Experience\")\nplt.ylabel(\"Salary\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:45:22.858322Z","iopub.execute_input":"2024-09-30T17:45:22.859100Z","iopub.status.idle":"2024-09-30T17:45:23.127137Z","shell.execute_reply.started":"2024-09-30T17:45:22.859049Z","shell.execute_reply":"2024-09-30T17:45:23.126046Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"index_list = [i for i in range(1, len(y_test)+1, 1)]  \nplt.plot(index_list, y_test, color='b', linestyle='-', label=\"Real Values\")  \nplt.plot(index_list, y_hat, color='r', linestyle='-', label=\"Predicted Values\")  \nplt.title(\"Comparison Between Real Test Values and Predicted Values\")\nplt.legend()  # Added legend to distinguish lines\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:46:22.938089Z","iopub.execute_input":"2024-09-30T17:46:22.939344Z","iopub.status.idle":"2024-09-30T17:46:23.373881Z","shell.execute_reply.started":"2024-09-30T17:46:22.939292Z","shell.execute_reply":"2024-09-30T17:46:23.372709Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## **Evaluation of Linear Regression**","metadata":{}},{"cell_type":"code","source":"#Calculate Mean Squared Error\nmse = mean_squared_error(y_test, y_hat)","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:48:09.134091Z","iopub.execute_input":"2024-09-30T17:48:09.135009Z","iopub.status.idle":"2024-09-30T17:48:09.143267Z","shell.execute_reply.started":"2024-09-30T17:48:09.134963Z","shell.execute_reply":"2024-09-30T17:48:09.142143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Displaying MSE\nprint('Mean Squared Error :',mse)","metadata":{"execution":{"iopub.status.busy":"2024-09-30T17:48:13.435616Z","iopub.execute_input":"2024-09-30T17:48:13.436044Z","iopub.status.idle":"2024-09-30T17:48:13.441773Z","shell.execute_reply.started":"2024-09-30T17:48:13.436003Z","shell.execute_reply":"2024-09-30T17:48:13.440618Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}