def run_pred_census_ln(subset_df, census_year):
"""
This function takes a dataframe of teacher information and
runs the Pred Census Ln Function.
Input:
- subset_df: a dataframe that is a subset of teacher information
Output:
- df: a dataframe with a predicted race imputation
"""
has_last_name_df = subset_df[subset_df.teacher_last.notnull()].copy()
df = pred_census_ln(has_last_name_df, 'teacher_last', census_year)
#recode two race categories
recode_dict = {'api': 'asian'}
# replace values using generalized race categories
df.replace(to_replace=recode_dict, value=None, inplace=True)
# keep only the race column
cols_to_keep = ['race']
df = df[cols_to_keep]
df.rename(columns={'race': 'census_lastname'}, inplace=True)
return df
def guessActorInfo(actor_name):
# If NNDB bio page not found then use SexMachine or ethnicolr module to guess gender/race
print("\t\tNNDB bio page not found...Using Python modules to guess")
first_name = actor_name.split(" ")[0]
gender_guessed = gender_detector.get_gender(first_name)
if gender_guessed == "andy":
print("\t\tUsing getGenders utility")
# gender_guessed = getGenders(first_name)[0][0]
gender_guessed = "Male"
if gender_guessed in gender_table.keys():
gender = gender_table[gender_guessed]
else:
gender = "Others"
last_name = " ".join(actor_name.split(" ")[1:])
last_name_df = pd.DataFrame([{'name': last_name}])
race_guessed = pred_census_ln(last_name_df, 'name')["race"][0]
if race_guessed in race_table.keys():
race = race_table[race_guessed]
else:
race = "Others"
print("\t\tGuess:(" + gender_guessed + "," + race_guessed + ")")
return (gender, race)
def predict_ethnicity_1(df: pd.DataFrame, name_attr: str) -> pd.DataFrame:
df1 = ec.pred_census_ln(df, name_attr, year=2010).iloc[:, -4:]
df1.columns = ['asian', 'black', 'hispanic', 'white']
df1.index = df.index
df.drop(columns='race', inplace=True)
return df1
#!/usr/bin/python
# -*- coding: utf-8 -*-
import pandas as pd
from ethnicolr import census_ln, pred_census_ln
names = [{'name': 'smith'}, {'name': 'zhang'}, {'name': 'jackson'}]
df = pd.DataFrame(names)
print(df)
print(census_ln(df, 'name'))
print(census_ln(df, 'name', 2010))
print(pred_census_ln(df, 'name'))
logging.info("ending the get username program at " +
str(datetime.datetime.now()))
logging.info("total: " + str(count))
myFile.close
#adding race prediction
logging.info("adding race prediction")
print("adding race prediction")
df = pd.read_csv("tmp_" + filename,
usecols=[
'username', 'firstname', 'lastname', 'groupname',
'recordingTime', 'num_record', 'num_groupuser'
])
df = pd.DataFrame(df)
dict = {}
result = pred_census_ln(df, 'lastname')
result.to_csv(filename, sep=',')
logging.info("finished race prediction")
print("finished race prediction")
print(filename)
#f.write(str(datetime.datetime.now())+","+str(count)+","+str(client.get_participants(channel,limit = 0).total)+","+channel[13:])
#f.close()
#adding to database
#filename = "dx_chain_user_first.csv"
#groupname = "dxchain"
#connect to database
print("connecting db")
import pandas as pd
import numpy as np
import csv
import sys
from ethnicolr import census_ln, pred_census_ln
filepath = sys.argv[1]
file = pd.read_csv(filepath)
dataframe_stat = pred_census_ln(file, 'LAST NAME', 2010)
refreshed_dataframe = dataframe_stat[['FIRST NAME', 'LAST NAME', 'race']]
refreshed_dataframe.columns = ['FIRST NAME', 'LAST NAME', 'ETHNICITY']
refreshed_dataframe.to_csv('Consumer_Data_10394_Sample2.csv', index=False)