kururu-abdo

df_can = pd.read_csv('https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/Data%20Files/Canada.csv')

print('Data downloaded and read into a dataframe!')

! wget --quiet https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/Data%20Files/world_countries.json
    
print('GeoJSON file downloaded!')

world_geo = r'https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/Data%20Files/world_countries.json' # geojson file

kururu-abdo

import numpy as np  # useful for many scientific computing in Python
import pandas as pd #
#!pip3 install folium==0.5.0
import folium

print('Folium installed and imported!')

# define the world map
world_map = folium.Map()

kururu-abdo

from wordcloud import WordCloud, STOPWORDS

print ('Wordcloud imported!')

import urllib

# # open the file and read it into a variable alice_novel
alice_novel = urllib.request.urlopen('https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DV0101EN-SkillsNetwork/Data%20Files/alice_novel.txt').read().decode("utf-8")

stopwords = set(STOPWORDS)

kururu-abdo

def create_waffle_chart(categories, values, height, width, colormap, value_sign=''):

    # compute the proportion of each category with respect to the total
    total_values = sum(values)
    category_proportions = [(float(value) / total_values) for value in values]

    # compute the total number of tiles
    total_num_tiles = width * height # total number of tiles
    print ('Total number of tiles is', total_num_tiles)
    

kururu-abdo

# we can use the sum() method to get the total population per year
df_tot = pd.DataFrame(df_can[years].sum(axis=0))

# change the years to type int (useful for regression later on)
df_tot.index = map(int, df_tot.index)

# reset the index to put in back in as a column in the df_tot dataframe
df_tot.reset_index(inplace = True)

# rename columns

kururu-abdo

df_can.sort_values(['Total'], ascending=False, axis=0, inplace=True)

# get the top 5 entries
df_top5 = df_can.head()

# transpose the dataframe
df_top5 = df_top5[years].transpose()

df_top5.head()

kururu-abdo

import numpy as np  # useful for many scientific computing in Python
import pandas as pd # primary data structure library

%matplotlib inline 

import matplotlib as mpl
import matplotlib.pyplot as plt

### type your answer here
df_CI = df_can.loc[['India', 'China'], years]

kururu-abdo

//drop columns
df.drop(['Unnamed: 0.1', 'Unnamed: 0'], axis=1, inplace=True)


//count sample or get dimensions
x_train_pr1.shape

kururu-abdo

import matplotlib.pyplot as plt
%matplotlib inline 

#box plot   // to show relation between 
sns.boxplot(x="body-style", y="price", data=df)


#reg plot    -- to show relation degree
sns.regplot(x="peak-rpm", y="price", data=df)

kururu-abdo

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler

Input=[('scale',StandardScaler()),('model',LinearRegression())]

pipe=Pipeline(Input)

pipe.fit(df[['horsepower' ,'col1']],y)

ypipe=pipe.predict(df[['horsepower' ,'col1'])