Exploring DataFrames

Exploring DataFrames

import pandas as pd
df = pd.read_csv('data.csv')

df.head()         # first 5 rows
df.tail(10)       # last 10 rows
df.sample(5)      # 5 random rows

df.shape          # (rows, cols)
df.columns        # column names
df.dtypes         # data types
df.info()         # overview + nulls
df.describe()     # statistics for numeric cols

# Missing values
df.isnull().sum()      # nulls per column
df.isnull().any()      # bool per column
df.notnull().sum()

# Unique values
df['status'].unique()
df['status'].nunique()
df['status'].value_counts()
df['status'].value_counts(normalize=True)  # percentages