In [1]:

    

import pandas as pd
import matplotlib.pyplot as plt
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
print(norm_reviews[:5])


    

    




                             FILM  RT_user_norm  Metacritic_user_nom  \
0  Avengers: Age of Ultron (2015)           4.3                 3.55   
1               Cinderella (2015)           4.0                 3.75   
2                  Ant-Man (2015)           4.5                 4.05   
3          Do You Believe? (2015)           4.2                 2.35   
4   Hot Tub Time Machine 2 (2015)           1.4                 1.70   

   IMDB_norm  Fandango_Ratingvalue  
0       3.90                   4.5  
1       3.55                   4.5  
2       3.90                   4.5  
3       2.70                   4.5  
4       2.55                   3.0  

In [2]:

    

fandango_ratings_freq_cnts = norm_reviews['Fandango_Ratingvalue'].value_counts()

fandango_distribution = fandango_ratings_freq_cnts.sort_index()

imdb_freq = norm_reviews['IMDB_norm'].value_counts()
imdb_distribution = imdb_freq.sort_index()

print(fandango_distribution)

print(imdb_distribution)


    

    




2.7     2
2.8     2
2.9     5
3.0     4
3.1     3
3.2     5
3.3     4
3.4     9
3.5     9
3.6     8
3.7     9
3.8     5
3.9    12
4.0     7
4.1    16
4.2    12
4.3    11
4.4     7
4.5     9
4.6     4
4.8     3
Name: Fandango_Ratingvalue, dtype: int64
2.00     1
2.10     1
2.15     1
2.20     1
2.30     2
2.45     2
2.50     1
2.55     1
2.60     2
2.70     4
2.75     5
2.80     2
2.85     1
2.90     1
2.95     3
3.00     2
3.05     4
3.10     1
3.15     9
3.20     6
3.25     4
3.30     9
3.35     7
3.40     1
3.45     7
3.50     4
3.55     7
3.60    10
3.65     5
3.70     8
3.75     6
3.80     3
3.85     4
3.90     9
3.95     2
4.00     1
4.05     1
4.10     4
4.15     1
4.20     2
4.30     1
Name: IMDB_norm, dtype: int64

In [3]:

    

fig, ax = plt.subplots()

ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(0,5))

print(norm_reviews['Fandango_Ratingvalue'].value_counts().sort_index(ascending=False))
plt.show()


    

    




4.8     3
4.6     4
4.5     9
4.4     7
4.3    11
4.2    12
4.1    16
4.0     7
3.9    12
3.8     5
3.7     9
3.6     8
3.5     9
3.4     9
3.3     4
3.2     5
3.1     3
3.0     4
2.9     5
2.8     2
2.7     2
Name: Fandango_Ratingvalue, dtype: int64






    

In [7]:

    

#range for histograms will be same accros all plots
#this is important when analyzing data distribution across multiple columns
#since hist will make bins in range of min and max values for the column
valuespan = (0,5)

fig = plt.figure(figsize=(5,20))
ax1 = fig.add_subplot(4,1,1)
ax2 = fig.add_subplot(4,1,2)
ax3 = fig.add_subplot(4,1,3)
ax4 = fig.add_subplot(4,1,4)

ax1.hist(norm_reviews['Fandango_Ratingvalue'], bins=20, range=valuespan)
ax1.set_title('Distribution of Fandango Ratings')
ax1.set_ylim(0,50)
ax1.set_ylabel('Frequency')

ax2.hist(norm_reviews['RT_user_norm'], bins=20, range=valuespan)
ax2.set_title('Distribution of Rotten Tomatoes Ratings')
ax2.set_ylim(0,50)
ax2.set_ylabel('Frequency')

ax3.hist(norm_reviews['Metacritic_user_nom'], bins=20, range=valuespan)
ax3.set_title('Distribution of Metacritic Ratings')
ax3.set_ylim(0,50)
ax3.set_ylabel('Frequency')

ax4.hist(norm_reviews['IMDB_norm'], bins=20, range=valuespan)
ax4.set_title('Distribution of IMDB Ratings')
ax4.set_ylim(0,50)
ax4.set_ylabel('Frequency')

plt.show()


    

In [20]:

    

fig = plt.figure(figsize=(12,10))
ax = fig.add_subplot(2,1,1)
ax.boxplot(norm_reviews['RT_user_norm'])
ax.set_ylim(0,5)
ax.set_xlabel('Rotten Tomatoes')

ax1 = fig.add_subplot(2,1,2)
ax1.boxplot(norm_reviews['IMDB_norm'])
ax1.set_ylim(0,5)
ax1.set_xlabel('IMDB ratings')

plt.show()


    

In [24]:

    

#lets plot all box diagrams for all rating columns in the same plot
fig,ax = plt.subplots()
# ignore FILM column cols[0]
ax.boxplot(norm_reviews[cols[1:]].values)
ax.set_xticklabels(cols[1:], rotation=90)
#it is important to set lim on values when making histogram or boxplot for multiple columns, cuz their max and min values can differ
ax.set_ylim(0,5)

plt.show()


    

In [ ]: