Day 9 - Network data exercise

import pandas as pd # read in data df_ship = pd.read_excel("shipping1997.xlsx") df_states = pd.read_excel("shipping1997.xlsx", sheet_name=1) df_comm = pd.read_excel("shipping1997.xlsx", sheet_name=2) df_dist = pd.read_excel("shipping1997.xlsx", sheet_name=3)

# create copy of df_ship df_ship2 = df_ship.copy() # state abbreviations-names dictionary abbr = pd.Series(df_states['State'].values, index=df_states['Abbreviation']).to_dict() # replace abbreviations with names df_ship2 = df_ship2.replace({'origin': abbr}) df_ship2 = df_ship2.replace({'dest': abbr}) df_ship2.head()

# convert adjacent column to boolean df_dist['adjacent'] = df_dist['adjacent'].astype('bool') df_dist.head()

# merge df_dist and df_ship df_ship_dist = pd.merge(df_ship, df_dist, how='left', on=['origin', 'dest']) df_ship_dist.head()