dradecic

b0, b1 = 0.0, 1.0

lr = 0.001
epochs = 10000
error = []

# run 10000 times
for epoch in range(epochs):
    # initialize to 0 -> cost of epoch, Jb_0, Jb_1
    epoch_cost, cost_b0, cost_b1 = 0, 0, 0

dradecic

ratings_df = pd.DataFrame()
ratings_df['Mean_Rating'] = data.groupby('title')['rating'].mean().values
ratings_df['Num_Ratings'] = data.groupby('title')['rating'].count().values


fig, ax = plt.subplots(figsize=(14, 7))
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)
ax.set_title('Rating vs. Number of Ratings', fontsize=24, pad=20)
ax.set_xlabel('Rating', fontsize=16, labelpad=20)

dradecic

data.sort_values(by='numRatings', ascending=False).drop_duplicates('movieId')[:10]

dradecic

num_ratings = pd.DataFrame(data.groupby('movieId').count()['rating']).reset_index()
data = pd.merge(left=data, right=num_ratings, on='movieId')
data.rename(columns={'rating_x': 'rating', 'rating_y': 'numRatings'}, inplace=True)

dradecic

values = defaultdict(list)
for ind, row in data.iterrows():
    for genre in row['genres'].split('|'):
        values[genre].append(row['rating'])
        
        
genre_lst, rating_lst = [], []
for key, item in values.items():
    if key not in [0, 1]:
        genre_lst.append(key)

dradecic

def make_bar_chart(dataset, attribute, bar_color='#3498db', edge_color='#2980b9', title='Title', xlab='X', ylab='Y', sort_index=False):
    if sort_index == False:
        xs = dataset[attribute].value_counts().index
        ys = dataset[attribute].value_counts().values
    else:
        xs = dataset[attribute].value_counts().sort_index().index
        ys = dataset[attribute].value_counts().sort_index().values
        
    
    fig, ax = plt.subplots(figsize=(14, 7))

dradecic

genre_df = pd.DataFrame(data['genres'].str.split('|').tolist(), index=data['movieId']).stack()
genre_df = genre_df.reset_index([0, 'movieId'])
genre_df.columns = ['movieId', 'Genre']

dradecic

def make_histogram(dataset, attribute, bins=25, bar_color='#3498db', edge_color='#2980b9', title='Title', xlab='X', ylab='Y', sort_index=False):
    if attribute == 'moviePubYear':
        dataset = dataset[dataset['moviePubYear'] != 9999]
        
    fig, ax = plt.subplots(figsize=(14, 7))
    ax.spines['top'].set_visible(False)
    ax.spines['right'].set_visible(False)
    ax.set_title(title, fontsize=24, pad=20)
    ax.set_xlabel(xlab, fontsize=16, labelpad=20)
    ax.set_ylabel(ylab, fontsize=16, labelpad=20)

dradecic

years = []

for title in data['title']:
    year_subset = title[-5:-1]
    try: years.append(int(year_subset))
    except: years.append(9999)
        
data['moviePubYear'] = years
print(len(data[data['moviePubYear'] == 9999]))

dradecic

%matplotlib inline

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from collections import defaultdict

# read CSVs
movies = pd.read_csv('data/movies.csv')
ratings = pd.read_csv('data/ratings.csv')