2.5 Survey data mining with a gender perspective

PHOTO

Tue Aug 31 2021 18:43:42 GMT+0000 (Coordinated Universal Time)

Saved by @saraortiz #python

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches
import numpy as np

df_gender = pd.read_csv('data/prepared/Survey_on_Gender_Equality_At_Home/Survey_on_Gender_Equality_At_Home_2_cleaned.csv')

df = df_gender.copy()
df.head()

df = df[['Country','Gender','Internet_Penetration','a1_agree','b7_full']]
df.rename(columns={'a1_agree':'Equal_Rights','b7_full':'Access_Money'},inplace=True)

print(df['Internet_Penetration'].unique())

df = df[df['Internet_Penetration']!='.']
df['Internet_Penetration'] = [float(df.loc[i,'Internet_Penetration'][:2]) 
                              if df.loc[i,'Internet_Penetration'][1].isalnum() 
                              else float(df.loc[i,'Internet_Penetration'][:1]) for i in df.index]
                              
print(df['Equal_Rights'].unique())

df[df['Equal_Rights']==19]['Country']

df = df[df['Equal_Rights']!=19] #Remove outlier

figure, axes = plt.subplots(3,1,figsize=(10,15))
sns.regplot(x=df['Internet_Penetration'],y=df['Equal_Rights'],ax=axes[0]).set(
    title='Internet penetration vs Equal rights perception',xlabel='',ylabel='')
df_female = df[df['Gender']=='Female']
sns.regplot(x=df_female['Internet_Penetration'],y=df_female['Access_Money'],ax=axes[1]).set(
    title='Internet penetration vs self access of money',xlabel='',ylabel='')
sns.regplot(x=df_female['Equal_Rights'],y=df_female['Access_Money'],ax=axes[2]).set(
    title='Equal rights perception vs Self access of money',xlabel='',ylabel='')
plt.show()

fig = plt.figure(figsize=(7,6)) 
sns.heatmap(df_female.corr(),annot=True).set_title('Correlation')
plt.show()

df_gender = df

df_business = pd.read_csv('data/prepared/Survey_on_future_business/Survey_on_future_business_good_clean.csv')
df = df_business.copy()
df.head()
df['statistic'] = round(df['statistic']/df['total_asked']*100,2)

df_codes = pd.read_csv('data/prepared/Country_Code.csv')
df_codes.head()

df_codes = df_codes[[ 'Country','Alpha-2 code']]

df = df_codes.merge(df,left_on='Alpha-2 code',right_on='country')

df.drop(columns=['country','who_was_asked','total_asked'],inplace=True)
df = df[(df['variable'] == "gen_opn_1_text") | (df['variable'] == "own_fem_text")]

df.replace(['gen_opn_1_text','own_fem_text'],['Self_perp_equal_rights','Owner_female'],inplace=True)

print(df['value'].unique())

df.dropna(inplace=True)
df.reset_index(drop=True,inplace=True)
df

for var in df['variable'].unique():
    for val in df[df['variable']==var]['value'].unique():
        df[var+'_'+val] = [df.loc[i,'statistic'] if (df.loc[i,'variable']==var) 
                           & (df.loc[i,'value']==val) else np.nan for i in df.index]
df = df.groupby(['Country']).sum().drop(columns=['statistic'])
df

df['Equal_rights_agree'] = df['Self_perp_equal_rights_Agree'] + df['Self_perp_equal_rights_Strongly agree']
df['Equal_rights_disagree'] = df['Self_perp_equal_rights_Disagree'] + df[
                                'Self_perp_equal_rights_Strongly disagree']
df['Female_owner_Half_or_more'] = df['Owner_female_All owners are female'] + df[
                                'Owner_female_Exactly half'] + df['Owner_female_More than half']
df['Female_owner_less_than_half'] = df['Owner_female_Less than half'] + df['Owner_female_None']
df = df[['Equal_rights_agree','Equal_rights_disagree','Female_owner_Half_or_more',
         'Female_owner_less_than_half']]
df

figure, axes = plt.subplots(1,1,figsize=(9,5))
sns.regplot(x=df['Equal_rights_agree'],y=df['Female_owner_Half_or_more']).set(
    title='Equal rights perception vs proportion of female owner of business',xlabel='',ylabel='')
plt.show()

df_business = df.reset_index()
df = df_gender.merge(df_business,on='Country')
df_female = df[df['Gender']=='Female'] 
df_female

figure, axes = plt.subplots(2,1,figsize=(15,12))
sns.regplot(x=df_female['Access_Money'],y=df_female['Female_owner_Half_or_more'],ax=axes[0]).set(
    title='Self access of money vs Female_owner_Half_or_more',xlabel='',ylabel='')
sns.regplot(x=df_female['Internet_Penetration'],y=df_female['Female_owner_Half_or_more'],ax=axes[1]).set(
    title='Internet penetration vs Female_owner_Half_or_more',xlabel='',ylabel='')

plt.show()

Save snippets that work from anywhere online with our extensions

Available in the Chrome Web Store

Get Firefox Add-on

Get VS Code extension

Comments

More like this

Importing images from a directory (Python) to list or dictionary

from PIL import Image
import glob
image_list = []
for filename in glob.glob('yourpath/*.gif'): #assuming gif
    im=Image.open(filename)
    image_list.append(im)

python - Find out the percentage of missing values in each column in the given dataset - Stack Overflow

percent_missing = df.isnull().sum() * 100 / len(df)
missing_value_df = pd.DataFrame({'column_name': df.columns,
                                 'percent_missing': percent_missing})

#python #python #loops #whileloop

Print the name of 7 days in a week - by using while loop

days = 0
week = [‘Monday’, ‘Tuesday’, ‘Wednesday’, ‘Thursday’, ‘Friday’, ‘Saturday’, 3.‘Sunday’]
while day < 7:
print(“Today is” + week[days])
days += 1

Getting the index of an item in a list containing it in Python

>>> ["foo", "bar", "baz"].index("bar")
1

#python #python #strings #vowels #function

Get vowels in strings

This method gets vowels (‘a’, ‘e’, ‘i’, ‘o’, ‘u’) found in a string.
   
#make a function:
def get_vowels(string):

#return is the keyword which means function have to return value: 
 return [each for each in string if each in 'aeiou']


#assign the words and function will return vowels words.
get_vowels('foobar') # ['o', 'o', 'a']


get_vowels('gym') # []

Could not build wheels for tokenizers which use PEP 517 and cannot be installed directly

https://github.com/pydata/bottleneck/issues/281

How To Bypass Cloudflare Bot Protection In Selenium - CodingTutz

options = webdriver.ChromeOptions()
options.add_experimental_option("excludeSwitches", ["enable-automation"])
options.add_experimental_option('useAutomationExtension', False)
options.add_argument("--disable-blink-features=AutomationControlled")
driver = webdriver.Chrome(options=options)

#javascript #python #search #historicalcode #google #algorithms

Google’s PageRank Algorithm from 1996 - the origin of internet search

import numpy as np

def pagerank(M, num_iterations=100, d=0.85):
    N = M.shape[1]
    v = np.random.rand(N, 1)
    v = v / np.linalg.norm(v, 1)
    iteration = 0
    while iteration < num_iterations:
        iteration += 1
        v = d * np.matmul(M, v) + (1 - d) / N
    return v

Python Loop through Excel sheets, place into one df - Stack Overflow

import pandas as pd

sheets_dict = pd.read_excel('Book1.xlsx', sheetname=None)

full_table = pd.DataFrame()
for name, sheet in sheets_dict.items():
    sheet['sheet'] = name
    sheet = sheet.rename(columns=lambda x: x.split('\n')[-1])
    full_table = full_table.append(sheet)

full_table.reset_index(inplace=True, drop=True)

print full_table

#python #dates #functions #python3.8

How to parse a String into Datetime in Python

from datetime import datetime

datetime_object = datetime.strptime('Jun 1 2005  1:33PM', '%b %d %Y %I:%M%p')

python - Way to change Google Chrome user agent in Selenium? - Stack Overflow

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from fake_useragent import UserAgent

options = Options()
ua = UserAgent()
userAgent = ua.random
print(userAgent)
options.add_argument(f'user-agent={userAgent}')
driver = webdriver.Chrome(chrome_options=options, executable_path=r'C:\WebDrivers\ChromeDriver\chromedriver_win32\chromedriver.exe')
driver.get("https://www.google.co.in")
driver.quit()

python - How to see the progress bar of read_csv - Stack Overflow

def read_csv_pgbar(csv_path, chunksize, usecols, dtype=object):


    # print('Getting row count of csv file')

    rows = sum(1 for _ in open(csv_path, 'r')) - 1 # minus the header
    # chunks = rows//chunksize + 1
    # print('Reading csv file')
    chunk_list = []

    with tqdm(total=rows, desc='Rows read: ') as bar:
        for chunk in pd.read_csv(csv_path, chunksize=chunksize, usecols=usecols, dtype=dtype):
            chunk_list.append(chunk)
            bar.update(len(chunk))

    df = pd.concat((f for f in chunk_list), axis=0)
    print('Finish reading csv file')

    return df

#python #python #lists #dictionary

Convert two lists into a dictionary

keys, values)) # {'a': 2, 'c': 4, 'b': 3}
 
 
#make a function: def is the keyword for the function:
def to_dictionary(keys, values):
 
 
#return is the keyword that tells program that function has to return value   
return dict(zip(keys, values))
 
  
 
# keys and values are the lists:
 
keys = ["a", "b", "c"]   
 
values = [2, 3, 4]

Convert string to Enum in Python - Stack Overflow

>>> from enum import Enum
>>> class Build(Enum):
...   debug = 200
...   build = 400
... 

Build['debug']

Raising errors in Python

my_list = [27, 5, 9, 6, 8]

def RemoveValue(myVal):
    if myVal not in my_list:
        raise ValueError("Value must be in the given list")
    else:
        my_list.remove(myVal)
    return my_list

print(RemoveValue(27))
print(RemoveValue(27))

Browse more snippets >>