This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) | |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# 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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
//drop columns | |
df.drop(['Unnamed: 0.1', 'Unnamed: 0'], axis=1, inplace=True) | |
//count sample or get dimensions | |
x_train_pr1.shape |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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']) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def PlotPolly(model, independent_variable, dependent_variabble, Name): | |
x_new = np.linspace(15, 55, 100) | |
y_new = model(x_new) | |
plt.plot(independent_variable, dependent_variabble, '.', x_new, y_new, '-') | |
plt.title('Polynomial Fit with Matplotlib for Price ~ Length') | |
ax = plt.gca() | |
ax.set_facecolor((0.898, 0.898, 0.898)) | |
fig = plt.gcf() | |
plt.xlabel(Name) |