Inclusive Nepal

# Pandas
import pandas as pd
#Mapbox
from mapboxgl.utils import *
from mapboxgl.viz import *

df = pd.read_csv("data_sources/disability_2011.csv")

df.head()

df.head()

df_geojson = pd.read_json('data_sources/map.geojson')

df_geojson.head()

df.set_index("District", inplace=True)

def add_data(features):
    name = features.get('properties').get('name')
    if (name in df.index):
        percentage = df.loc[name]['Percentage of PWDs']
        population = df.loc[name]['Population with Disability']
        features['properties'] = {'name': name, 'percentage': percentage, 'population':population}
        return features

df_geojson.features.apply(add_data)

features = df_geojson['features'].values.tolist()

my_dict = {"type":"FeatureCollection", "features":features}

token  = "pk................................................................"

viz = ChoroplethViz(my_dict, 
                     access_token=token,
                     color_property='population',
                     color_stops=create_color_stops([0, 2500, 5000, 7500, 10000, 12500], colors='YlOrRd'),
                     color_function_type='interpolate',
                     line_stroke='--',
                     line_color='rgb(128,0,38)',
                     line_width=1,
                     opacity=0.8,
                     center=(84, 28.5), 
                     zoom=6
                    )
viz.show()

viz = ChoroplethViz(my_dict, 
                     access_token=token,
                     color_property='percentage',
                     color_stops=create_color_stops([0, 1, 2, 3, 4], colors='YlOrRd'),
                     color_function_type='interpolate',
                     line_stroke='--',
                     line_color='rgb(128,0,38)',
                     line_width=1,
                     opacity=0.8,
                     center=(84, 28.5), 
                     zoom=6
                    )
viz.show()

df.sort_values(['Population with Disability'], ascending=False).head()

import pandas as pd
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen
import seaborn as sns

site = "https://www.onlinekhabar.com/"
hdr = {'User-Agent': 'Mozilla/5.0'}
req = Request(site,headers=hdr)
page = urlopen(req)
soup = BeautifulSoup(page, "lxml")

image_count = 0
alt_count = 0 
collection = soup.findAll("img")
for img in collection:
    image_count = image_count + 1
    if 'alt' in img.attrs:
        alt_count = alt_count + 1
print ("image_count", image_count) 
print ("alt_count", alt_count) 
print ("alt_count_percent", alt_count/image_count*100)

df = pd.read_csv('data_sources/news_portals.csv')

df

def alt_counter(site):
    try:
        hdr = {'User-Agent': 'Mozilla/5.0'}
        req = Request(site, headers=hdr)
        page = urlopen(req)
        soup = BeautifulSoup(page, "lxml")
        image_count = 0
        alt_count = 0 
        collection = soup.findAll("img")
        for img in collection:
            image_count = image_count + 1
            if 'alt' in img.attrs:
                alt_count = alt_count + 1
        return (alt_count, image_count)
    except:
        return (None, None)

df['alt_count'],df['image_count']=zip(*df.Link.apply(alt_counter))

df

df['percent'] = 100*df['alt_count']/df['image_count']

df

sns.barplot(y='Portal', x='percent', data=df)