3vivekb

def addr_cleaner(addr):
    '''Split up an address based on typical address markers, 
        because words after the marker tend to mess up geocoding.
        addr = '1509 DENTONA PL  NEW SFR LOT 3 PLAN B3'
        returns - > '1509 DENTONA PL '
    '''
    address_words = [' AV ', ' DR ', ' PL ', ' ST ', ' WY ', ' RD ', ' LN ',' CT ',' CL ', ' BL ', ' SQ ']
#     print(addr)
    for ad in address_words:
        new_addr = addr.split(ad)

3vivekb

import pandas as pd
import glob

#Combine multiple csv's into one df
allFiles = glob.glob('.' + "/gps_*.csv")
frame = pd.DataFrame()
frames = []
for file_ in allFiles:
    df = pd.read_csv(file_, header=0)
    frames.append(df)

3vivekb

# List unique values in a DataFrame column
pd.unique(df.column_name.ravel())

# Convert Series datatype to numeric, getting rid of any non-numeric values
df['col'] = df['col'].astype(str).convert_objects(convert_numeric=True)

# Grab DataFrame rows where column has certain values
valuelist = ['value1', 'value2', 'value3']
df = df[df.column.isin(valuelist)]