Machine Learning - Machine Learning Development Life Cycle - Understanding your Data Tutorial

1. How big is the data?

# size of row and column

df.shape()

2. What does the data look like?

# first five-row

df.head()

# to get random row sample

df.sample(5)

3. What is the data type of cols?

# to get datatype, non-null value

df.info()

4. Are there any missing values?

# to check null value

df.isnull().sum()

5. How does the data look mathematically?

# to check mean, min, max, std deviation

df.describe()

6. Are there duplicated values?

df.duplicated.sum()

7. How is the correlation between cols?

# To check the correlation between two variables – pearson corr

df.corr()

8. How to count each category?

df[‘Survived’].value_counts()

9. How to check mean, min, max, skewness

df[‘age’].mean()

df[‘age’].min()

df[‘age’].max()

df[‘age’].skew()