ymanzi / dslr

Datascience X Logistic Regression

Subject: Dslr

Member: 🌜 Ymanzi 🌛

How to Use It

➣ Make train

Will train the model with the dataset and generate a file theta.csv with the weights used for prediction python3.8 logreg_train.py DATASET_NAME.csv

➣ Make predict

Will generate a prediction file houses.csv from the dataset and a csv file containing the weights python3.8 logreg_predict.py DATASET_NAME.csv WEIGHTS.csv

Resources

• Logistic Regression Explained
• Logistic Regression Module 8
• Gradient descent optimization
• Stochastic gradient descent
• Youtube - Logistic Regression
• Youtube - Introduction to Logistic Regression

Visualization

➣ Make describe

python3.8 describe.py DATASET_NAME.csv

Display information for all numerical features.

➣ Make histo

python3.8 histogram.py DATASET_NAME.csv

Display a histogram answering the question:

• Which Hogwarts course has a homogeneous score distribution between all four houses?

➣ Make pair

python3.8 pair_plot.py DATASET_NAME.csv

Display a pair plot answering the question:

• From this visualization, what features are you going to use for your logistic regression??

➣ Make scatter

python3.8 scatter_plot.py DATASET_NAME.csv

Display a scatter plot answering the question:

• What are the two features that are similar ?