Comparer les révisions

Corentin Vande Kerckhove · Corentin Vande Kerckhove · ad371dbe · ad371dbe · ad371dbe · ad371dbe
--- a/data-collection/docextraction.ipynb
+++ b/data-collection/docextraction.ipynb
--- a/data-collection/exercise1.ipynb
+++ b/data-collection/exercise1.ipynb
+%% Cell type:markdown id: tags:
+
+# Exercise 1 - Parsing HTML
+The following notebook is greatly inspired by https://github.com/khuyentran1401/Web-Scrapping-Wikipedia
+
 %% Cell type:code id: tags:

 ``` python
 import requests
 import urllib.request
 import time
 from bs4 import BeautifulSoup
 import numpy as np
 import pandas as pd
 from urllib.request import urlopen
+
+DATA_REPO =
 ```

 %% Cell type:code id: tags:

 ``` python
 url = 'https://en.wikipedia.org/wiki/Epidemiology_of_depression'
 ```

 %% Cell type:code id: tags:

 ``` python
 html = urlopen(url)
 ```

 %% Cell type:code id: tags:

 ``` python
 soup = BeautifulSoup(html, 'html.parser')
 ```

 %% Cell type:code id: tags:

 ``` python
 tables = soup.find_all('table')
 ```

 %% Cell type:code id: tags:

 ``` python
 #convert number as string to integer
 #re.sub() returns the substring that match the regrex
 import re
 def process_num(num):
    return float(re.sub(r'[^\w\s.]','',num))
 ```

 %% Cell type:code id: tags:

 ``` python
 num1 = re.sub(r'[^\w\s.]','','1,156.30')
 num1
 ```

 %% Output

    '1156.30'

 %% Cell type:code id: tags:

 ``` python
 ranks = []
 rates = []
 countries = []
 links = []

 for table in tables:
    rows = table.find_all('tr')

    for row in rows:
        cells = row.find_all('td')

        if len(cells) > 1:
            rank = cells[0]
            ranks.append(int(rank.text))

            country = cells[1]
            countries.append(country.text.strip())

            rate = cells[2]
            rates.append(process_num(rate.text.strip()))

            link = cells[1].find('a').get('href')
            links.append('https://en.wikipedia.org/'+ link)

 df1 = pd.DataFrame(ranks, index= countries, columns = ['Rank'])
 df1['DALY rate'] = rates

 df1.head(10)
 ```

 %% Output

                   Rank  DALY rate
    United States     1    1454.74
    Nepal             2    1424.48
    East Timor        3    1404.10
    Bangladesh        4    1401.53
    India             5    1400.84
    Pakistan          6    1400.42
    Brazil            7    1396.10
    Maldives          8    1391.61
    Bhutan            9    1385.53
    Afghanistan      10    1385.14

 %% Cell type:code id: tags:

 ``` python
 sun_url = urlopen('https://en.wikipedia.org/wiki/List_of_cities_by_sunshine_duration')
 sun = BeautifulSoup(sun_url, 'html.parser')
 tables = sun.find_all('table')

 #Dictionary to hold the name of the country and its corresponding temperature
 country_suns = {}

 #Dictionary to hold the country and its frequency in the table
 count = {}
 for table in tables:
    if len(table) >1:
        rows = table.find_all('tr')

        #Skip the first row, which is the name of the columns
        for row in rows[1:]:
            cells = row.find_all('td')
            country = cells[0].text.strip()

            #If country in the list of country we found previously
            #append the country to the dictionary
            if country in countries:

                sun = cells[-2].text.strip()
                sun = process_num(sun)/10

                #If country is already in the dictionary
                #add to the existing sun hours of that country and the count to keep track of how many times we add
                if country in country_suns:
                    count[country] += 1
                    country_suns[country] += sun

                else:
                    count[country] = 1
                    country_suns[country] = sun


 #Find the average temperature of each country
 for country in country_suns:
    print(country_suns[country],count[country])
    country_suns[country] = round(country_suns[country]/count[country],2)
    print('Country: {}, Sunshine Hours: {}'.format(country,country_suns[country]))

 ```

 %% Output

    789.14 3
    Country: Benin, Sunshine Hours: 263.05
    515.99 2
    Country: Togo, Sunshine Hours: 258.0
    710.25 3
    Country: Ghana, Sunshine Hours: 236.75
    866.0500000000001 4
    Country: Cameroon, Sunshine Hours: 216.51
    344.03999999999996 2
    Country: Gabon, Sunshine Hours: 172.02
    1334.54 5
    Country: Nigeria, Sunshine Hours: 266.91
    711.91 2
    Country: Sudan, Sunshine Hours: 355.95
    336.1 1
    Country: Eritrea, Sunshine Hours: 336.1
    641.8 2
    Country: Burkina Faso, Sunshine Hours: 320.9
    320.32 1
    Country: Niger, Sunshine Hours: 320.32
    670.6400000000001 2
    Country: Chad, Sunshine Hours: 335.32
    307.0 1
    Country: Gambia, Sunshine Hours: 307.0
    629.2 2
    Country: Senegal, Sunshine Hours: 314.6
    620.5999999999999 2
    Country: Somalia, Sunshine Hours: 310.3
    327.9 1
    Country: Djibouti, Sunshine Hours: 327.9
    964.0099999999999 3
    Country: Mali, Sunshine Hours: 321.34
    653.3 2
    Country: Algeria, Sunshine Hours: 326.65
    609.99 2
    Country: Tunisia, Sunshine Hours: 305.0
    946.64 3
    Country: Morocco, Sunshine Hours: 315.55
    2253.8500000000004 6
    Country: Egypt, Sunshine Hours: 375.64
    635.6199999999999 2
    Country: Libya, Sunshine Hours: 317.81
    1212.01 4
    Country: Kenya, Sunshine Hours: 303.0
    234.1 1
    Country: Angola, Sunshine Hours: 234.1
    1213.1399999999999 4
    Country: Tanzania, Sunshine Hours: 303.28
    556.97 2
    Country: Ethiopia, Sunshine Hours: 278.49
    666.5 2
    Country: Mauritania, Sunshine Hours: 333.25
    1884.79 6
    Country: South Africa, Sunshine Hours: 314.13
    1028.0 3
    Country: Botswana, Sunshine Hours: 342.67
    889.6400000000001 3
    Country: Zambia, Sunshine Hours: 296.55
    613.08 2
    Country: Zimbabwe, Sunshine Hours: 306.54
    838.76 3
    Country: Malawi, Sunshine Hours: 279.59
    1718.66 6
    Country: Madagascar, Sunshine Hours: 286.44
    283.8 1
    Country: Mozambique, Sunshine Hours: 283.8
    681.8 3
    Country: Uganda, Sunshine Hours: 227.27
    237.34 1
    Country: Burundi, Sunshine Hours: 237.34
    488.0 2
    Country: Guinea, Sunshine Hours: 244.0
    270.7 1
    Country: Guinea-Bissau, Sunshine Hours: 270.7
    309.79 2
    Country: Equatorial Guinea, Sunshine Hours: 154.9
    747.5 2
    Country: Namibia, Sunshine Hours: 373.75
    317.51 1
    Country: Afghanistan, Sunshine Hours: 317.51
    220.74 1
    Country: Azerbaijan, Sunshine Hours: 220.74
    206.6 1
    Country: Bangladesh, Sunshine Hours: 206.6
    1091.49 5
    Country: China, Sunshine Hours: 218.3
    973.66 4
    Country: India, Sunshine Hours: 243.41
    298.33000000000004 1
    Country: Indonesia, Sunshine Hours: 298.33
    282.61 1
    Country: Iran, Sunshine Hours: 282.61
    324.08000000000004 1
    Country: Iraq, Sunshine Hours: 324.08
    331.1 1
    Country: Israel, Sunshine Hours: 331.1
    361.71000000000004 2
    Country: Japan, Sunshine Hours: 180.86
    486.29999999999995 2
    Country: Kazakhstan, Sunshine Hours: 243.15
    279.15 1
    Country: Mongolia, Sunshine Hours: 279.15
    249.2 1
    Country: North Korea, Sunshine Hours: 249.2
    349.33000000000004 1
    Country: Oman, Sunshine Hours: 349.33
    598.4300000000001 2
    Country: Pakistan, Sunshine Hours: 299.22
    210.31 1
    Country: Philippines, Sunshine Hours: 210.31
    1578.2299999999998 8
    Country: Russia, Sunshine Hours: 197.28
    647.3 2
    Country: Saudi Arabia, Sunshine Hours: 323.65
    202.24 1
    Country: Singapore, Sunshine Hours: 202.24
    439.33000000000004 2
    Country: South Korea, Sunshine Hours: 219.67
    870.0099999999999 4
    Country: Thailand, Sunshine Hours: 217.5
    466.76 2
    Country: Turkey, Sunshine Hours: 233.38
    282.39 1
    Country: Uzbekistan, Sunshine Hours: 282.39
    849.4 4
    Country: Vietnam, Sunshine Hours: 212.35
    254.4 1
    Country: Albania, Sunshine Hours: 254.4
    247.4 1
    Country: Armenia, Sunshine Hours: 247.4
    188.4 1
    Country: Austria, Sunshine Hours: 188.4
    180.7 1
    Country: Belarus, Sunshine Hours: 180.7
    154.6 1
    Country: Belgium, Sunshine Hours: 154.6
    176.9 1
    Country: Bosnia and Herzegovina, Sunshine Hours: 176.9
    217.7 1
    Country: Bulgaria, Sunshine Hours: 217.7
    191.3 1
    Country: Croatia, Sunshine Hours: 191.3
    166.8 1
    Country: Czech Republic, Sunshine Hours: 166.8
    331.40999999999997 1
    Country: Cyprus, Sunshine Hours: 331.41
    173.9 1
    Country: Denmark, Sunshine Hours: 173.9
    182.6 1
    Country: Estonia, Sunshine Hours: 182.6
    185.8 1
    Country: Finland, Sunshine Hours: 185.8
    449.8 2
    Country: France, Sunshine Hours: 224.9
    204.6 1
    Country: Georgia, Sunshine Hours: 204.6
    328.79999999999995 2
    Country: Germany, Sunshine Hours: 164.4
    595.0 2
    Country: Greece, Sunshine Hours: 297.5
    198.8 1
    Country: Hungary, Sunshine Hours: 198.8
    132.6 1
    Country: Iceland, Sunshine Hours: 132.6
    145.3 1
    Country: Ireland, Sunshine Hours: 145.3
    438.8 2
    Country: Italy, Sunshine Hours: 219.4
    175.4 1
    Country: Latvia, Sunshine Hours: 175.4
    169.1 1
    Country: Lithuania, Sunshine Hours: 169.1
    305.4 1
    Country: Malta, Sunshine Hours: 305.4
    212.6 1
    Country: Moldova, Sunshine Hours: 212.6
    166.2 1
    Country: Netherlands, Sunshine Hours: 166.2
    166.8 1
    Country: Norway, Sunshine Hours: 166.8
    157.1 1
    Country: Poland, Sunshine Hours: 157.1
    280.6 1
    Country: Portugal, Sunshine Hours: 280.6
    211.5 1
    Country: Romania, Sunshine Hours: 211.5
    203.8 1
    Country: Slovakia, Sunshine Hours: 203.8
    197.4 1
    Country: Slovenia, Sunshine Hours: 197.4
    826.6 3
    Country: Spain, Sunshine Hours: 275.53
    374.29999999999995 2
    Country: Sweden, Sunshine Hours: 187.15
    156.6 1
    Country: Switzerland, Sunshine Hours: 156.6
    195.5 1
    Country: Ukraine, Sunshine Hours: 195.5
    306.0 2
    Country: United Kingdom, Sunshine Hours: 153.0
    1825.24 9
    Country: Canada, Sunshine Hours: 202.8
    225.98000000000002 1
    Country: Honduras, Sunshine Hours: 225.98
    1038.5 4
    Country: Mexico, Sunshine Hours: 259.62
    275.99 1
    Country: Nicaragua, Sunshine Hours: 275.99
    174.35 1
    Country: Panama, Sunshine Hours: 174.35
    295.7 1
    Country: El Salvador, Sunshine Hours: 295.7
    15218.579999999998 54
    Country: United States, Sunshine Hours: 281.83
    1149.52 5
    Country: Argentina, Sunshine Hours: 229.9
    228.89000000000001 1
    Country: Bolivia, Sunshine Hours: 228.89
    1322.58 6
    Country: Brazil, Sunshine Hours: 220.43
    953.81 6
    Country: Colombia, Sunshine Hours: 158.97
    1324.27 5
    Country: Chile, Sunshine Hours: 264.85
    381.90999999999997 2
    Country: Ecuador, Sunshine Hours: 190.95
    280.3 1
    Country: Paraguay, Sunshine Hours: 280.3
    604.0 3
    Country: Peru, Sunshine Hours: 201.33
    248.14000000000001 1
    Country: Uruguay, Sunshine Hours: 248.14
    579.0899999999999 2
    Country: Venezuela, Sunshine Hours: 289.54
    2553.15 9
    Country: Australia, Sunshine Hours: 283.68
    192.2 1
    Country: Fiji, Sunshine Hours: 192.2
    613.1999999999999 3
    Country: New Zealand, Sunshine Hours: 204.4
    246.3 1
    Country: Papua New Guinea, Sunshine Hours: 246.3
    233.0 1
    Country: Solomon Islands, Sunshine Hours: 233.0

 %% Cell type:code id: tags:

 ``` python
 df2 = pd.DataFrame.from_dict(country_suns,orient='index', columns = ['Sunshine Hours/Year'])

 df = df1.join(df2)

 df.info()
 ```

 %% Output

    <class 'pandas.core.frame.DataFrame'>
    Index: 192 entries, United States to Japan
    Data columns (total 3 columns):
    Rank                   192 non-null int64
    DALY rate              192 non-null float64
    Sunshine Hours/Year    122 non-null float64
    dtypes: float64(2), int64(1)
    memory usage: 11.0+ KB

 %% Cell type:code id: tags:

 ``` python
 df.dropna(inplace=True)
 ```

 %% Cell type:code id: tags:

 ``` python
 df.info()

 import matplotlib.pyplot as plt
 import seaborn as sns

 sns.scatterplot('Rank', 'Sunshine Hours/Year', data=df)
 ```

 %% Output

    <class 'pandas.core.frame.DataFrame'>
    Index: 122 entries, United States to Japan
    Data columns (total 3 columns):
    Rank                   122 non-null int64
    DALY rate              122 non-null float64
    Sunshine Hours/Year    122 non-null float64
    dtypes: float64(2), int64(1)
    memory usage: 8.8+ KB

    <matplotlib.axes._subplots.AxesSubplot at 0x1a1a728410>



 %% Cell type:code id: tags:

 ``` python
 df.corr()
 ```

 %% Output

                             Rank  DALY rate  Sunshine Hours/Year
    Rank                 1.000000  -0.963597             0.346623
    DALY rate           -0.963597   1.000000            -0.285906
    Sunshine Hours/Year  0.346623  -0.285906             1.000000

 %% Cell type:code id: tags:

 ``` python
 ```

+%% Cell type:markdown id: tags:
+
+# Exercise 1 - Parsing HTML
+The following notebook is greatly inspired by https://github.com/khuyentran1401/Web-Scrapping-Wikipedia
+
 %% Cell type:code id: tags:

 ``` python
 import requests
 import urllib.request
 import time
 from bs4 import BeautifulSoup
 import numpy as np
 import pandas as pd
 from urllib.request import urlopen
+
+DATA_REPO =
 ```

 %% Cell type:code id: tags:

 ``` python
 url = 'https://en.wikipedia.org/wiki/Epidemiology_of_depression'
 ```

 %% Cell type:code id: tags:

 ``` python
 html = urlopen(url)
 ```

 %% Cell type:code id: tags:

 ``` python
 soup = BeautifulSoup(html, 'html.parser')
 ```

 %% Cell type:code id: tags:

 ``` python
 tables = soup.find_all('table')
 ```

 %% Cell type:code id: tags:

 ``` python
 #convert number as string to integer
 #re.sub() returns the substring that match the regrex
 import re
 def process_num(num):
    return float(re.sub(r'[^\w\s.]','',num))
 ```

 %% Cell type:code id: tags:

 ``` python
 num1 = re.sub(r'[^\w\s.]','','1,156.30')
 num1
 ```

 %% Output

    '1156.30'

 %% Cell type:code id: tags:

 ``` python
 ranks = []
 rates = []
 countries = []
 links = []

 for table in tables:
    rows = table.find_all('tr')

    for row in rows:
        cells = row.find_all('td')

        if len(cells) > 1:
            rank = cells[0]
            ranks.append(int(rank.text))

            country = cells[1]
            countries.append(country.text.strip())

            rate = cells[2]
            rates.append(process_num(rate.text.strip()))

            link = cells[1].find('a').get('href')
            links.append('https://en.wikipedia.org/'+ link)

 df1 = pd.DataFrame(ranks, index= countries, columns = ['Rank'])
 df1['DALY rate'] = rates

 df1.head(10)
 ```

 %% Output

                   Rank  DALY rate
    United States     1    1454.74
    Nepal             2    1424.48
    East Timor        3    1404.10
    Bangladesh        4    1401.53
    India             5    1400.84
    Pakistan          6    1400.42
    Brazil            7    1396.10
    Maldives          8    1391.61
    Bhutan            9    1385.53
    Afghanistan      10    1385.14

 %% Cell type:code id: tags:

 ``` python
 sun_url = urlopen('https://en.wikipedia.org/wiki/List_of_cities_by_sunshine_duration')
 sun = BeautifulSoup(sun_url, 'html.parser')
 tables = sun.find_all('table')

 #Dictionary to hold the name of the country and its corresponding temperature
 country_suns = {}

 #Dictionary to hold the country and its frequency in the table
 count = {}
 for table in tables:
    if len(table) >1:
        rows = table.find_all('tr')

        #Skip the first row, which is the name of the columns
        for row in rows[1:]:
            cells = row.find_all('td')
            country = cells[0].text.strip()

            #If country in the list of country we found previously
            #append the country to the dictionary
            if country in countries:

                sun = cells[-2].text.strip()
                sun = process_num(sun)/10

                #If country is already in the dictionary
                #add to the existing sun hours of that country and the count to keep track of how many times we add
                if country in country_suns:
                    count[country] += 1
                    country_suns[country] += sun

                else:
                    count[country] = 1
                    country_suns[country] = sun


 #Find the average temperature of each country
 for country in country_suns:
    print(country_suns[country],count[country])
    country_suns[country] = round(country_suns[country]/count[country],2)
    print('Country: {}, Sunshine Hours: {}'.format(country,country_suns[country]))

 ```

 %% Output

    789.14 3
    Country: Benin, Sunshine Hours: 263.05
    515.99 2
    Country: Togo, Sunshine Hours: 258.0
    710.25 3
    Country: Ghana, Sunshine Hours: 236.75
    866.0500000000001 4
    Country: Cameroon, Sunshine Hours: 216.51
    344.03999999999996 2
    Country: Gabon, Sunshine Hours: 172.02
    1334.54 5
    Country: Nigeria, Sunshine Hours: 266.91
    711.91 2
    Country: Sudan, Sunshine Hours: 355.95
    336.1 1
    Country: Eritrea, Sunshine Hours: 336.1
    641.8 2
    Country: Burkina Faso, Sunshine Hours: 320.9
    320.32 1
    Country: Niger, Sunshine Hours: 320.32
    670.6400000000001 2
    Country: Chad, Sunshine Hours: 335.32
    307.0 1
    Country: Gambia, Sunshine Hours: 307.0
    629.2 2
    Country: Senegal, Sunshine Hours: 314.6
    620.5999999999999 2
    Country: Somalia, Sunshine Hours: 310.3
    327.9 1
    Country: Djibouti, Sunshine Hours: 327.9
    964.0099999999999 3
    Country: Mali, Sunshine Hours: 321.34
    653.3 2
    Country: Algeria, Sunshine Hours: 326.65
    609.99 2
    Country: Tunisia, Sunshine Hours: 305.0
    946.64 3
    Country: Morocco, Sunshine Hours: 315.55
    2253.8500000000004 6
    Country: Egypt, Sunshine Hours: 375.64
    635.6199999999999 2
    Country: Libya, Sunshine Hours: 317.81
    1212.01 4
    Country: Kenya, Sunshine Hours: 303.0
    234.1 1
    Country: Angola, Sunshine Hours: 234.1
    1213.1399999999999 4
    Country: Tanzania, Sunshine Hours: 303.28
    556.97 2
    Country: Ethiopia, Sunshine Hours: 278.49
    666.5 2
    Country: Mauritania, Sunshine Hours: 333.25
    1884.79 6
    Country: South Africa, Sunshine Hours: 314.13
    1028.0 3
    Country: Botswana, Sunshine Hours: 342.67
    889.6400000000001 3
    Country: Zambia, Sunshine Hours: 296.55
    613.08 2
    Country: Zimbabwe, Sunshine Hours: 306.54
    838.76 3
    Country: Malawi, Sunshine Hours: 279.59
    1718.66 6
    Country: Madagascar, Sunshine Hours: 286.44
    283.8 1
    Country: Mozambique, Sunshine Hours: 283.8
    681.8 3
    Country: Uganda, Sunshine Hours: 227.27
    237.34 1
    Country: Burundi, Sunshine Hours: 237.34
    488.0 2
    Country: Guinea, Sunshine Hours: 244.0
    270.7 1
    Country: Guinea-Bissau, Sunshine Hours: 270.7
    309.79 2
    Country: Equatorial Guinea, Sunshine Hours: 154.9
    747.5 2
    Country: Namibia, Sunshine Hours: 373.75
    317.51 1
    Country: Afghanistan, Sunshine Hours: 317.51
    220.74 1
    Country: Azerbaijan, Sunshine Hours: 220.74
    206.6 1
    Country: Bangladesh, Sunshine Hours: 206.6
    1091.49 5
    Country: China, Sunshine Hours: 218.3
    973.66 4
    Country: India, Sunshine Hours: 243.41
    298.33000000000004 1
    Country: Indonesia, Sunshine Hours: 298.33
    282.61 1
    Country: Iran, Sunshine Hours: 282.61
    324.08000000000004 1
    Country: Iraq, Sunshine Hours: 324.08
    331.1 1
    Country: Israel, Sunshine Hours: 331.1
    361.71000000000004 2
    Country: Japan, Sunshine Hours: 180.86
    486.29999999999995 2
    Country: Kazakhstan, Sunshine Hours: 243.15
    279.15 1
    Country: Mongolia, Sunshine Hours: 279.15
    249.2 1
    Country: North Korea, Sunshine Hours: 249.2
    349.33000000000004 1
    Country: Oman, Sunshine Hours: 349.33
    598.4300000000001 2
    Country: Pakistan, Sunshine Hours: 299.22
    210.31 1
    Country: Philippines, Sunshine Hours: 210.31
    1578.2299999999998 8
    Country: Russia, Sunshine Hours: 197.28
    647.3 2
    Country: Saudi Arabia, Sunshine Hours: 323.65
    202.24 1
    Country: Singapore, Sunshine Hours: 202.24
    439.33000000000004 2
    Country: South Korea, Sunshine Hours: 219.67
    870.0099999999999 4
    Country: Thailand, Sunshine Hours: 217.5
    466.76 2
    Country: Turkey, Sunshine Hours: 233.38
    282.39 1
    Country: Uzbekistan, Sunshine Hours: 282.39
    849.4 4
    Country: Vietnam, Sunshine Hours: 212.35
    254.4 1
    Country: Albania, Sunshine Hours: 254.4
    247.4 1
    Country: Armenia, Sunshine Hours: 247.4
    188.4 1
    Country: Austria, Sunshine Hours: 188.4
    180.7 1
    Country: Belarus, Sunshine Hours: 180.7
    154.6 1
    Country: Belgium, Sunshine Hours: 154.6
    176.9 1
    Country: Bosnia and Herzegovina, Sunshine Hours: 176.9
    217.7 1
    Country: Bulgaria, Sunshine Hours: 217.7
    191.3 1
    Country: Croatia, Sunshine Hours: 191.3
    166.8 1
    Country: Czech Republic, Sunshine Hours: 166.8
    331.40999999999997 1
    Country: Cyprus, Sunshine Hours: 331.41
    173.9 1
    Country: Denmark, Sunshine Hours: 173.9
    182.6 1
    Country: Estonia, Sunshine Hours: 182.6
    185.8 1
    Country: Finland, Sunshine Hours: 185.8
    449.8 2
    Country: France, Sunshine Hours: 224.9
    204.6 1
    Country: Georgia, Sunshine Hours: 204.6
    328.79999999999995 2
    Country: Germany, Sunshine Hours: 164.4
    595.0 2
    Country: Greece, Sunshine Hours: 297.5
    198.8 1
    Country: Hungary, Sunshine Hours: 198.8
    132.6 1
    Country: Iceland, Sunshine Hours: 132.6
    145.3 1
    Country: Ireland, Sunshine Hours: 145.3
    438.8 2
    Country: Italy, Sunshine Hours: 219.4
    175.4 1
    Country: Latvia, Sunshine Hours: 175.4
    169.1 1
    Country: Lithuania, Sunshine Hours: 169.1
    305.4 1
    Country: Malta, Sunshine Hours: 305.4
    212.6 1
    Country: Moldova, Sunshine Hours: 212.6
    166.2 1
    Country: Netherlands, Sunshine Hours: 166.2
    166.8 1
    Country: Norway, Sunshine Hours: 166.8
    157.1 1
    Country: Poland, Sunshine Hours: 157.1
    280.6 1
    Country: Portugal, Sunshine Hours: 280.6
    211.5 1
    Country: Romania, Sunshine Hours: 211.5
    203.8 1
    Country: Slovakia, Sunshine Hours: 203.8
    197.4 1
    Country: Slovenia, Sunshine Hours: 197.4
    826.6 3
    Country: Spain, Sunshine Hours: 275.53
    374.29999999999995 2
    Country: Sweden, Sunshine Hours: 187.15
    156.6 1
    Country: Switzerland, Sunshine Hours: 156.6
    195.5 1
    Country: Ukraine, Sunshine Hours: 195.5
    306.0 2
    Country: United Kingdom, Sunshine Hours: 153.0
    1825.24 9
    Country: Canada, Sunshine Hours: 202.8
    225.98000000000002 1
    Country: Honduras, Sunshine Hours: 225.98
    1038.5 4
    Country: Mexico, Sunshine Hours: 259.62
    275.99 1
    Country: Nicaragua, Sunshine Hours: 275.99
    174.35 1
    Country: Panama, Sunshine Hours: 174.35
    295.7 1
    Country: El Salvador, Sunshine Hours: 295.7
    15218.579999999998 54
    Country: United States, Sunshine Hours: 281.83
    1149.52 5
    Country: Argentina, Sunshine Hours: 229.9
    228.89000000000001 1
    Country: Bolivia, Sunshine Hours: 228.89
    1322.58 6
    Country: Brazil, Sunshine Hours: 220.43
    953.81 6
    Country: Colombia, Sunshine Hours: 158.97
    1324.27 5
    Country: Chile, Sunshine Hours: 264.85
    381.90999999999997 2
    Country: Ecuador, Sunshine Hours: 190.95
    280.3 1
    Country: Paraguay, Sunshine Hours: 280.3
    604.0 3
    Country: Peru, Sunshine Hours: 201.33
    248.14000000000001 1
    Country: Uruguay, Sunshine Hours: 248.14
    579.0899999999999 2
    Country: Venezuela, Sunshine Hours: 289.54
    2553.15 9
    Country: Australia, Sunshine Hours: 283.68
    192.2 1
    Country: Fiji, Sunshine Hours: 192.2
    613.1999999999999 3
    Country: New Zealand, Sunshine Hours: 204.4
    246.3 1
    Country: Papua New Guinea, Sunshine Hours: 246.3
    233.0 1
    Country: Solomon Islands, Sunshine Hours: 233.0

 %% Cell type:code id: tags:

 ``` python
 df2 = pd.DataFrame.from_dict(country_suns,orient='index', columns = ['Sunshine Hours/Year'])

 df = df1.join(df2)

 df.info()
 ```

 %% Output

    <class 'pandas.core.frame.DataFrame'>
    Index: 192 entries, United States to Japan
    Data columns (total 3 columns):
    Rank                   192 non-null int64
    DALY rate              192 non-null float64
    Sunshine Hours/Year    122 non-null float64
    dtypes: float64(2), int64(1)
    memory usage: 11.0+ KB

 %% Cell type:code id: tags:

 ``` python
 df.dropna(inplace=True)
 ```

 %% Cell type:code id: tags:

 ``` python
 df.info()

 import matplotlib.pyplot as plt
 import seaborn as sns

 sns.scatterplot('Rank', 'Sunshine Hours/Year', data=df)
 ```

 %% Output

    <class 'pandas.core.frame.DataFrame'>
    Index: 122 entries, United States to Japan
    Data columns (total 3 columns):
    Rank                   122 non-null int64
    DALY rate              122 non-null float64
    Sunshine Hours/Year    122 non-null float64
    dtypes: float64(2), int64(1)
    memory usage: 8.8+ KB

    <matplotlib.axes._subplots.AxesSubplot at 0x1a1a728410>



 %% Cell type:code id: tags:

 ``` python
 df.corr()
 ```

 %% Output

                             Rank  DALY rate  Sunshine Hours/Year
    Rank                 1.000000  -0.963597             0.346623
    DALY rate           -0.963597   1.000000            -0.285906
    Sunshine Hours/Year  0.346623  -0.285906             1.000000

 %% Cell type:code id: tags:

 ``` python
 ```

--- a/link-analysis/floyd.py
+++ b/link-analysis/floyd.py
--- a/link-analysis/preprocess.py
+++ b/link-analysis/preprocess.py
--- a/link-analysis/to_complete.py
+++ b/link-analysis/to_complete.py
--- a/text-mining/textanalysis.ipynb
+++ b/text-mining/textanalysis.ipynb
--- a/data/a1_city_sunshine_duration.html
+++ b/data/a1_city_sunshine_duration.html
--- a/data/a1_epidemiology_of_depression.html
+++ b/data/a1_epidemiology_of_depression.html
No results found