JLFDataScience

#We extract a list of existing acronyms in the section of the Madrid Stock Exchange within yahoo finances in the Spanish version
ScrapedAux = sourceCode_tickers.split('components":{"components":')[1].split('],')[0].split(',')[0:-1]
print(ScrapedAux[:10])

JLFDataScience

sourceCode_tickers = str(urlopen('https://es.finance.yahoo.com/quote/IGBM.MA/components?p=IGBM.MA').read())
print(sourceCode_tickers)

JLFDataScience

# List of fields we will scrape
list_of_fields = ['Market Cap', 'Enterprise Value', 'Trailing P/E', 'Forward P/E', 'PEG Ratio', 'Price/Sales', 'Price/Book', 'Enterprise Value/Revenue', 'Enterprise Value/EBITDA', 'Fiscal Year Ends', 'Most Recent Quarter', 'Profit Margin', 'Operating Margin', 'Return on Assets', 'Return on Equity', 'Revenue', 'Revenue Per Share', 'Quarterly Revenue Growth', 'Gross Profit', 'EBITDA', 'Net Income Avi to Common', 'Diluted EPS', 'Quarterly Earnings Growth', 'Total Cash', 'Total Cash Per Share', 'Total Debt', 'Total Debt/Equity', 'Current Ratio', 'Book Value Per Share', 'Operating Cash Flow', 'Levered Free Cash Flow', 'Beta', '52-Week Change', 'S&P500 52-Week Change', '52 Week High', '52 Week Low', '50-Day Moving Average', '200-Day Moving Average', 'Avg Vol (3 month)', 'Avg Vol (10 day)', 'Shares Outstanding', 'Float', '% Held by Insiders', '% Held by Institutions', 'Shares Short', 'Short Ratio', 'Short % of Float', 'Shares Short (prior month)', 'Forward Annual Dividend Rate', '

JLFDataScience

#Importing libraries
from urllib.request import urlopen
import pandas as pd
import numpy as np
import time
import re

JLFDataScience

#We generate a list of user 21 movie titles to be able to add it to the functions.
#The df ratings is taken and the column movie_title.
user_film_21_list = ratings[ratings.user_id==user_21].movie_title.tolist()

recomendations_21_user = get_movie_recomendations(user_film_21_list)
recomendations_21_user.Titulo.head(20)

JLFDataScience

user_21 = 21
ratings[ratings.user_id==user_21].sort_values(by=['rating'], ascending=False)

JLFDataScience

#A function that returns the correlation vector for a movie
def get_similar_movie(movie):
    corr_matrix = np.corrcoef(ratings_matriz.T)
    movie_idx = list(movie_index).index(movie)
    return corr_matrix[movie_idx]

#We return movies that are more similar to the tastes of a model user.
#If we want to recommend movies to a user, we get the list of movies they've watched and add up the correlations
#of those movies with all the others to return the movies with a greater total correlation..
def get_movie_recomendations(user):

JLFDataScience

ratings_matriz = ratings.pivot_table(values='rating', index='user_id', columns='movie_title')

# We fill with 0 in the Nan values
ratings_matriz.fillna(0, inplace=True)

movie_index = ratings_matriz.columns

ratings_matriz.head()

JLFDataScience

#load the rantings file
ratings = pd.read_table('data/ratings.dat', header=None, sep='::', engine='python', names=['user_id', 'movie_id', 'rating', 'timestamp'])

#Deleted the date the rating was created
del ratings ['timestamp']

#Add the title of the film
ratings = pd.merge(ratings, movies_df, on='movie_id')[['user_id', 'movie_title', 'movie_id','rating']]

ratings.head()

JLFDataScience

# We get the genres of for example the first film, Toy Story
toy_story_features = movies_df.loc[0][movie_categories]
print(toy_story_features)

# We calculate the score of the film against the user through the vector product
toy_story_user_predicted_score = dot_product(toy_story_features, user_preferences.values())
toy_story_user_predicted_score
#5