pandas101.py

import pandas as pd
# .read_csv()
# .shape
# .head(N) .tail(N)
# .dtypes
# .loc[3, 'sepal_length'] .iloc
# .to_csv()


# pd.set_option('max_columns', 2)
# pd.options.display.float_format = '{:,.2f}'.format

# .isna()
# .cumsum(skipna=False)

# df['Profit'] = df.apply(lambda x:..., axis=1)
# df['Xx'].map()
# df.applymap(lambda x: len(str(x)))  # To every element


# .pivot .stack


# .plot()
# .plot.area(stacked=False)
# .boxplot()
# .describe()
# .corr()


# Packages
# - pandas_profiling
# from pandas_profiling import ProfileReport
# profile = ProfileReport(df, title="Title")
# profile.to_notebook_iframe()


# Dask - parallel computing
# import dask.dataframe as dd
# df = dd.read_csv('...')

# Koalas -> Pandas API to Apache Spark