Machine Learning Sandpit:

• Cover all related topics for the AWS ML certification

Making a change

#ML Data Basics:

#Pre-processing cheat sheet

1. Missing values
2. Categorical values
3. Normalize data
4. Standardize data
5. Feature extraction
6. Feature selection

#Data ingestion & validation

1. Missing value treatment
2. Imputation
3. Encoding (binary, one-hot)
4. Feature scaling
5. Feature engineering
6. Class imbalance

#Pandas Basics:

• df = pd.read_csv('data/test.csv')
• "df" is a Data Frame (A container object in pandas for holding structured data), pd.read returns this
• df.isnull().sum() is returning a structured output on the dataset for any fields with null values (zero)