Data Visualisation - Histogram and Boxplots

In [5]:

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
%config InlineBackend.figure_format = 'retina'

Data¶

In [2]:

reviews = pd.read_csv("fandango_score_comparison.csv")

In [4]:

reviews.head()

Out[4]:

	FILM	RottenTomatoes	RottenTomatoes_User	Metacritic	Metacritic_User	IMDB	Fandango_Stars	Fandango_Ratingvalue	RT_norm	RT_user_norm	...	IMDB_norm	RT_norm_round	RT_user_norm_round	Metacritic_norm_round	Metacritic_user_norm_round	IMDB_norm_round	Metacritic_user_vote_count	IMDB_user_vote_count	Fandango_votes	Fandango_Difference
0	Avengers: Age of Ultron (2015)	74	86	66	7.1	7.8	5.0	4.5	3.70	4.3	...	3.90	3.5	4.5	3.5	3.5	4.0	1330	271107	14846	0.5
1	Cinderella (2015)	85	80	67	7.5	7.1	5.0	4.5	4.25	4.0	...	3.55	4.5	4.0	3.5	4.0	3.5	249	65709	12640	0.5
2	Ant-Man (2015)	80	90	64	8.1	7.8	5.0	4.5	4.00	4.5	...	3.90	4.0	4.5	3.0	4.0	4.0	627	103660	12055	0.5
3	Do You Believe? (2015)	18	84	22	4.7	5.4	5.0	4.5	0.90	4.2	...	2.70	1.0	4.0	1.0	2.5	2.5	31	3136	1793	0.5
4	Hot Tub Time Machine 2 (2015)	14	28	29	3.4	5.1	3.5	3.0	0.70	1.4	...	2.55	0.5	1.5	1.5	1.5	2.5	88	19560	1021	0.5

5 rows × 22 columns

In [7]:

cols = ['FILM', 'RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
norm_reviews = reviews[cols]
norm_reviews.head()

Out[7]:

	FILM	RT_user_norm	Metacritic_user_nom	IMDB_norm	Fandango_Ratingvalue
0	Avengers: Age of Ultron (2015)	4.3	3.55	3.90	4.5
1	Cinderella (2015)	4.0	3.75	3.55	4.5
2	Ant-Man (2015)	4.5	4.05	3.90	4.5
3	Do You Believe? (2015)	4.2	2.35	2.70	4.5
4	Hot Tub Time Machine 2 (2015)	1.4	1.70	2.55	3.0

Frequency counts¶

In [14]:

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

Histogram¶

In [18]:

fig, ax = plt.subplots()
ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(0, 5))
plt.show()

In [19]:

fig, ax = plt.subplots()
ax.hist(norm_reviews['Fandango_Ratingvalue'], range=(0, 5), bins = 20)
plt.show()

In [25]:

fig = plt.figure(figsize=(15,8))
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax3 = fig.add_subplot(2,2,3)
ax4 = fig.add_subplot(2,2,4)


ax1.hist(norm_reviews["Fandango_Ratingvalue"], range = (0,5) , bins = 20)
ax1.set_ylim(0,50)
ax1.set_title("Distribution of Fandango Ratings")


ax2.hist(norm_reviews["RT_user_norm"], range = (0,5) , bins = 20)
ax2.set_ylim(0,50)
ax2.set_title("Distribution of Rotten Tomatoes Ratings")

ax3.hist(norm_reviews["Metacritic_user_nom"], range = (0,5) , bins = 20)
ax3.set_ylim(0,50)
ax3.set_title("Distribution of Metacritic Ratings")

ax4.hist(norm_reviews["IMDB_norm"], range = (0,5) , bins = 20)
ax4.set_ylim(0,50)
ax4.set_title("Distribution of IMDB Ratings")

Out[25]:

<matplotlib.text.Text at 0x122a497f0>

Boxplot¶

In [26]:

fig,ax = plt.subplots()

ax.boxplot(norm_reviews["RT_user_norm"])
ax.set_ylim(0,5)
ax.set_xticklabels(["Rotten Tomatoes"])

Out[26]:

[<matplotlib.text.Text at 0x122aa8550>]

Multiple Boxplots¶

In [29]:

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue']
fig, ax = plt.subplots(figsize = (10,8))
ax.boxplot(norm_reviews[num_cols].values)
ax.set_xticklabels(num_cols, rotation=90)
ax.set_ylim(0,5)
plt.show()