dottyz

stations = pd.concat([stations[~stations['station_id'].isnull()], no_ids])\
             .merge(bikeshare_stations[['station_id', 'lat', 'lon']], how='inner', on='station_id')\
             .drop_duplicates()
             
df = df.merge(stations, how='inner', left_on='from_station_name', right_on='name') \
       .merge(stations, how='inner', left_on='to_station_name', right_on='name', suffixes=['_from', '_to']) \
       .drop_duplicates()

df = df[[x for x in df.columns if not x.endswith('_station_id') and not x.endswith('_station_name') and x != 'trip_stop_time']]

dottyz

# Separate the stations without station IDs
no_ids = stations[stations['station_id'].isnull()]
for idx, miss in no_ids.iterrows():
    max_score = 0
    
    # Compare the similarity of the station without ID to each station in the API data
    for i, exist in bikeshare_stations[['station_id', 'name']].iterrows():
        score = fuzz.ratio(miss['name'], exist['name'])
        
        if score > 80 and score > max_score:

dottyz

stations_start = df[['from_station_id', 'from_station_name']]
stations_end = df[['to_station_id', 'to_station_name']]
stations_start.columns = stations_end.columns = ['station_id', 'name']

# Extracts the unique station ID and name combination from the from_station and to_station columns
stations = pd.concat([stations_start, stations_end]).dropna(how='all').drop_duplicates().reset_index(drop=True)

dottyz

# Identify the date structure used by each of the files as a dict:
#      * Key: data file name
#      * Value: [datetime format, hour difference bewteen timezone used and Eastern timezone]
date_formats = {
    'Bikeshare Ridership (2017 Q1).csv': ['%d/%m/%Y %H:%M', -4],
    'Bikeshare Ridership (2017 Q2).csv': ['%d/%m/%Y %H:%M', -4],
    'Bikeshare Ridership (2017 Q3).csv': ['%m/%d/%Y %H:%M', 0],
    'Bikeshare Ridership (2017 Q4).csv': ['%m/%d/%y %H:%M:%S', 0],
}
df = pd.DataFrame() # Initiate an empty DataFrame

dottyz

from datetime import timedelta
from fuzzywuzzy import fuzz

import matplotlib.pyplot as plt
import pandas as pd
import requests
import seaborn as sns

import json
import os