khuyentran1401

html = urlopen('https://www.themoviedb.org/list/4309')


bsObj = BeautifulSoup(html)
#Create 4 lists that contains all the url, movie's name, rank, and rating
urls = []
names = []
ranks = []
ratings = []
images = []

khuyentran1401

url = urlopen("https://www.themoviedb.org/movie/81")
soup = BeautifulSoup(url)


#find summary
soup.find('div', {'class':'overview'}).p.get_text()


#find director
soup.find('li', {'class':'profile'}).a.get_text()

khuyentran1401

#https://towardsdatascience.com/preprocessing-with-sklearn-a-complete-and-comprehensive-guide-670cb98fcfb9
X.dropna(axis=0, thresh=1, inplace=True)
#axis=0 is row, axis = 1 is colum
#thresh is the threshold (number of na) to drop the row or column
X.reset_index(inplace=True)
#reset the index and use the default one
X.drop(['index'], axis=1, inplace=True)
#drop old index column

khuyentran1401

m = read("filename.lp")

m.optimize()

m.printAttr("X")

khuyentran1401

#uniform, where all bins in each feature have identical widths.
#quantile (default), where all bins in each feature have the same number of points.
#kmeans, where all values in each bin have the same nearest center of a 1D k-means cluster.

from sklearn.preprocessing import KBinsDiscretizer
disc = KBinsDiscretizer(n_bins=3, encode='uniform', 
                        strategy='uniform')
disc.fit_transform(X)

khuyentran1401

from sklearn.preprocessing import FunctionTransformer

transformer = FunctionTransformer(np.log1p, validate=True)

transformer.fit_transform(X.f2.values.reshape(-1, 1)) #same output

X.f2.apply(lambda x : np.log1p(x)) #same output

khuyentran1401

import re

def processNum(num):
  return float(re.sub(r'[^\w\s.]','',num))

#https://regexr.com/

khuyentran1401

data = DataFrame({'k1': ['one'] * 3 + ['two'] * 4, 'k2': [1, 1, 2, 3, 3, 4, 4]})

#duplicated returns a boolean Series indicating whether each row is a duplicate or not:
data.duplicated()

#returns a DataFrame where the duplicated array is True:
data.drop_duplicates()

#specify the subset to detect duplicates
#filter based on column 'k1'

khuyentran1401

data = DataFrame({'food': ['bacon', 'pulled pork', 'bacon', 'Pastrami','corned beef', 'Bacon', 'pastrami', 'honey ham','nova lox'],'ounces': [4, 3, 12, 6,

#map between food to animal                                                                                                                        
meat_to_animal = {
'bacon': 'pig',
'pulled pork': 'pig',
'pastrami': 'cow',
'corned beef': 'cow',
'honey ham': 'pig',
'nova lox': 'salmon'

khuyentran1401

data = DataFrame(np.arange(12).reshape((3, 4)),index=['Ohio', 'Colorado', 'New York'],columns=['one', 'two', 'three', 'four'])

data.index.map(str.upper)
#Out: array([OHIO, COLORADO, NEW YORK], dtype=object)

data.index = data.index.map(str.upper)

#Alternative
data.rename(index=str.title, columns=str.upper)