def merger(dollars_divided, geo):
'''
Merges the dollars_divided and geo dataframes, coalescing the values across
matching columns. Drops unwanted columns. Returns a dataframe.
'''
# Define the arguments to merge_coalesce
keys = ['Address', 'City', 'State', 'ZipCode']
sfx = '_R'
how = 'left'
# Merge dollars_divided and geo together, filling in coordinates
df = u.merge_coalesce(dollars_divided, geo, keys, sfx, how)
# Drop these columns
df = df.drop([
'ClusterID', 'VendorName_LINK1', 'VendorName_LINK2', 'Name',
'CSDS_Vendor_ID_LINK2'
],
axis=1)
# Drop duplicates based only on this subset
subset = ['CSDS_Vendor_ID', 'Address', 'City', 'State', 'ZipCode']
return df.drop_duplicates(subset=subset).reset_index(drop=True)
def try_fill(df):
'''
Fills in missing zip codes and coordinates as best as possible. Copies in
values from elsewhere in the dataset and from the geocoded HQ addresses.
Returns a dataframe.
'''
# Print progress report
print('\nFilling in missing zip codes and coordinates as best as possible')
# Fill in missing zip codes as best as possible
targetsZ = ['ZipCode']
keys1Z = ['Address', 'City', 'State']
keys2Z = ['Name', 'Longitude', 'Latitude']
df = filler(df, targetsZ, str, keys1Z, keys2Z)
# Fill in missing longitude and latitude coordinates as best as possible
targetsL = ['Longitude', 'Latitude']
keys1L = ['Address', 'City', 'State', 'ZipCode']
keys2L = ['Name']
df = filler(df, targetsL, float, keys1L, keys2L)
# Read in the geocoded HQ addresses and fill in zip codes and coordinates as
# best as possible
geo = read_geo()
subset = ['Address', 'City', 'State']
df = u.merge_coalesce(df.reset_index(drop=True), geo, subset)
return df
def preprocess_contracts():
'''
Reads in the contract records. Preprocesses them to clean the amounts and
keep only those over the minimum amount specified in the MIN_DOLLARS
constant. Imports hand-collected addresses for Cook and IL contracts and
merges in addresses from IRS990 forms to fill in as many blanks as possible.
Returns a dataframe.
'''
# Read in the contracts and clean the dollar amounts
contracts = read_contracts()
contracts = clean_amounts(contracts)
# Read in the COOK addresses dataset
cook = import_addresses('cook')
# Fill in addresses from the COOK dataset, matching on VendorName; then,
# standardize VendorName
print('Coalescing COOK address matches')
merged = u.merge_coalesce(contracts, cook, 'VendorName')
merged['VendorName'] = merged['VendorName'].apply(stdname)
# Read in the IRS dataset
irs = import_addresses('irs')
# Get a datframe of JW similarity matches >= JWSIM_THRESH between the merged
# and irs dataframes
sfx = '_IRS'
jwsim = jwsim_contracts_irs(merged, irs, sfx)
# Print progress report
print('Coalescing IRS matches')
# Fill in addresses from the IRS dataset
coalesced = coalesce_matches(merged, jwsim, sfx)
# Read in the IL addresses dataset
il = import_addresses('il')
# Print progress report
print('Coalescing IL matches')
# Fill in addresses from the IL dataset, matching on VendorName
df = u.merge_coalesce(coalesced, il, 'VendorName')
return df
def coalesce_matches(contracts, jwsim, suffix):
'''
Pulls in the addresses from IRS records previously deemed to match the IL
agencies. Returns a dataframe.
'''
jwsim = trim_jwsim(jwsim, suffix)
# Define the key on which to coalesce
keys = ['CSDS_Contract_ID']
# Fill in missing values in contracts from matches in jwsim, matchin on keys
df = u.merge_coalesce(contracts, jwsim, keys, suffix)
return df
def fix_duplicate_addresses(df, key='ClusterID', target='Address_SVC'):
'''
Takes in a dataframe. Attempts to fix duplicate addresses (by default, in
the 'Address_SVC' field) if they have the same key (bby default, the
'ClusterID' field). Returns a dataframe.
'''
print('\nFixing duplicate addresses')
# Sort the target field by length, longest to shortest
sorter = df[target].str.len().sort_values(ascending=False).index
df = df.reindex(sorter)
# Make a mini version of the dataframe with two fields, the key & the target
# (which has been renamed to indicate it's the original field)
minimized_df = df[[key, target]].drop_duplicates().dropna()
minimized_df[target + '_Original'] = minimized_df[target]
# Make a list of the unique values in the key field
unique_keys = list(minimized_df[key].unique())
# Set a flag to FALSE
new_df_exists = False
# OVERVIEW: Call the iter_df() function on subsets of the dataframe (one
# subset per key) to compare and fix the address strings assigned to that
# key.
# For each value in the list of unique keys:
# Make a mini dataframe that is just the rows corresponding to that key
# If the there is more than 1 row:
# Call iter_df() on the mini df & assign the result to local_df2
# If the new_df_exists flag is set to TRUE:
# Create new_df by concatenating the existing new_df and local_df2
# else: Assign the name new_df to local_df2 and set the new_df_exists to TRUE
for uKey in unique_keys:
local_df = minimized_df[minimized_df[key] == uKey]
if len(local_df) > 1:
local_df2 = iter_df(
local_df.copy().drop_duplicates().reset_index(drop=True),
target)
if new_df_exists:
new_df = pd.concat([new_df, local_df2])
else:
new_df = local_df2
new_df_exists = True
print('Coalescing fixed addresses')
# Rename the columns in preparation of calling merge_coalesce()
new_cols = {target: target + '_COAL', target + '_Original': target}
new_df = new_df.rename(columns=new_cols, index=str)
# Rename the columns in preparation of calling merge_coalesce()
min_cols = {target + '_Original': target + '_COAL'}
minimized_df = minimized_df.rename(columns=min_cols, index=str)
# Coalesce with the dfs in this order so that we keep the new values
merged = u.merge_coalesce(new_df, minimized_df, [key, target], how='right')
# Merge the new address strings in, drop the original field, and rename the
# new one
df = df.merge(merged, how='left').drop(target, axis=1)
df = df.rename(columns={target + '_COAL': target}, index=str)
return df
