https://github.com/patilsukanya/assignment-05.-multiple-linear-regression-q2
Used libraries and functions as follows:
https://github.com/patilsukanya/assignment-05.-multiple-linear-regression-q2
collinearity-diagnostics cooks-distance correlation-analysis eda heteroscedasticity homoscedasticity leverage-score mlr multiple-linear-regression numpy ols-regression pairplot python regress-exog residual-analysis rsquare-values smf statsmodels vif
Last synced: 2 months ago
JSON representation
Used libraries and functions as follows:
- Host: GitHub
- URL: https://github.com/patilsukanya/assignment-05.-multiple-linear-regression-q2
- Owner: PatilSukanya
- Created: 2022-09-12T11:02:49.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-09-12T11:10:35.000Z (over 2 years ago)
- Last Synced: 2025-02-23T13:38:08.000Z (3 months ago)
- Topics: collinearity-diagnostics, cooks-distance, correlation-analysis, eda, heteroscedasticity, homoscedasticity, leverage-score, mlr, multiple-linear-regression, numpy, ols-regression, pairplot, python, regress-exog, residual-analysis, rsquare-values, smf, statsmodels, vif
- Language: Jupyter Notebook
- Homepage:
- Size: 337 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Assignment-05.-Multiple-Linear-Regression-Q2
Prepare a prediction model for profit of 50_startups data. Do transformations for getting better predictions of profit and make a table containing R^2 value for each prepared model. R&D Spend -- Research and devolop spend in the past few years Administration -- spend on administration in the past few years Marketing Spend -- spend on Marketing in the past few years State -- states from which data is collected Profit -- profit of each state in the past few years.
EDA
Correlation Analysis
Model Building
Model Testing
Model Validation Two Techniques: 1. Collinearity Check & 2. Residual Analysis.
Model Deletion Diagnostics (checking Outliers or Influencers) Two Techniques : 1. Cook's Distance & 2. Leverage value
Improving the Model
Model Deletion Diagnostics and Final Model
Model Predictions
table containing R^2 value for each prepared model