Day 20 of #100DaysOfCode

Task

1. Intermediate Machine Learning Course (40% done)
2. House price prediction

Resources

• Kaggle's Intermediate Machine Learning course

• • Lesson 1: Introduction - My Notebook
• • Lesson 2: Missing Values - My Notebook

• Lesson 3: Categorical Variables - My Notebook

• Kaggle House price prediction Challenge

• • My Notebook 1
• • My Notebook 2
• • My Notebook 3

Topics I have learnt

1. Intermediate Machine Learning Course

• Handling Missing values in data
• • by dropping columns
• • by imputing the mean values of the columns
• • by imputing the mean values and adding another column having True/False for respected imputed values
• Handling Categorical columns in data
• • by dropping categorical columns
• • Changing them to numbers using Ordinal Encoder
• • Creating each numerical column for every unique value using One Hot Encoding

2. Also House price prediction

• One by dropping missing columns using DecisionTreeRegressor.
• One by dropping missing columns using RandomForestRegressor.
• One by Imputing missing values, doing Ordinal Encoding using RandomForestRegressor.

Software used

• Jupyter Notebook
• Python 3.10.2
• Numpy 1.22.4
• pandas 1.4.2
• scikit-learn 1.1.1

My Notebooks

• L1 - Introduction.ipynb
• L2 - Missing_values.ipynb
• L3 - Categorical_variables.ipynb
• House_price_prediction_2.ipynb
• House_price_prediction_3.ipynb
• House_price_prediction_4.ipynb

Conclusion:

Today I learned how to handle misisng values using SimpleImputer and categorical columns using One Hot Encoding & Ordinal Encoding. Also, did house price prediction using DecisionTreeRegressor and RandomForestRegressor applied imputer & ordinal encoding too. Today was great!!!