Data Visualisation - Bars and Scatter Plots

In [1]:

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 [3]:

reviews.head()

Out[3]:

	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 [4]:

reviews.columns

Out[4]:

Index(['FILM', 'RottenTomatoes', 'RottenTomatoes_User', 'Metacritic',
       'Metacritic_User', 'IMDB', 'Fandango_Stars', 'Fandango_Ratingvalue',
       'RT_norm', 'RT_user_norm', 'Metacritic_norm', 'Metacritic_user_nom',
       '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'],
      dtype='object')

In [12]:

[x for x in reviews.columns if "norm" in x]

Out[12]:

['RT_norm',
 'RT_user_norm',
 'Metacritic_norm',
 'IMDB_norm',
 'RT_norm_round',
 'RT_user_norm_round',
 'Metacritic_norm_round',
 'Metacritic_user_norm_round',
 'IMDB_norm_round']

In [13]:

columns = ["FILM","RT_user_norm","Metacritic_user_nom","IMDB_norm","Fandango_Ratingvalue","Fandango_Stars"]

norm_reviews = reviews[columns]

In [14]:

norm_reviews.head()

Out[14]:

	FILM	RT_user_norm	Metacritic_user_nom	IMDB_norm	Fandango_Ratingvalue	Fandango_Stars
0	Avengers: Age of Ultron (2015)	4.3	3.55	3.90	4.5	5.0
1	Cinderella (2015)	4.0	3.75	3.55	4.5	5.0
2	Ant-Man (2015)	4.5	4.05	3.90	4.5	5.0
3	Do You Believe? (2015)	4.2	2.35	2.70	4.5	5.0
4	Hot Tub Time Machine 2 (2015)	1.4	1.70	2.55	3.0	3.5

In [31]:

# Positions of the left sides of the bars. [0.75, 1.75, 2.75, 3.75, 4.75]

fig, ax = plt.subplots()
bar_positions = np.arange(5) + 0.75

# Heights of the bars.  In our case, the average rating for the first movie in the dataset.
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.loc[0, num_cols].values

ax.bar(bar_positions, bar_heights)

Out[31]:

<Container object of 5 artists>

In [22]:

plt.bar(bar_positions,bar_heights)

Out[22]:

<Container object of 5 artists>

In [28]:

fig = plt.figure()
ax = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax.bar(bar_positions, bar_heights)
ax2.bar(bar_positions, bar_heights)

Out[28]:

<Container object of 5 artists>

Axis ticks ax.set_xticks( ) , ax.set_xticklabels( )¶

In [39]:

# Positions of the left sides of the bars. [0.75, 1.75, 2.75, 3.75, 4.75]

fig, ax = plt.subplots()
bar_positions = np.arange(5) + 0.75

# Heights of the bars.  In our case, the average rating for the first movie in the dataset.
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.loc[0, num_cols].values

ax.bar(bar_positions, bar_heights)
tick_positions = np.arange(1,6)
ax.set_xticks(tick_positions)
ax.set_xticklabels(num_cols, rotation = 90)

Out[39]:

[<matplotlib.text.Text at 0x11f330c50>,
 <matplotlib.text.Text at 0x11f30a8d0>,
 <matplotlib.text.Text at 0x11f4e9518>,
 <matplotlib.text.Text at 0x11f4ed048>,
 <matplotlib.text.Text at 0x11f4edb38>]

Full Example¶

In [40]:

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()

ax.bar(bar_positions, bar_heights, 0.5)
ax.set_xticks(tick_positions)
ax.set_xticklabels(num_cols, rotation=90)

ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()

Horizontal bar plot¶

In [47]:

num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.ix[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()

ax.barh(bar_positions, bar_heights, 0.5)
ax.set_yticks(tick_positions)
ax.set_yticklabels(num_cols)

ax.set_ylabel('Rating Source')
ax.set_xlabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()

In [49]:

fig,ax = plt.subplots()
ax.scatter(norm_reviews["Fandango_Ratingvalue"],norm_reviews["RT_user_norm"])
ax.set_xlabel("Fandango")
ax.set_ylabel("Rotten Tomatoes")

Out[49]:

<matplotlib.text.Text at 0x12083e8d0>

In [50]:

fig = plt.figure(figsize=(5,10))
ax1 = fig.add_subplot(2,1,1)
ax2 = fig.add_subplot(2,1,2)


ax1.scatter(norm_reviews["Fandango_Ratingvalue"],norm_reviews["RT_user_norm"])
ax1.set_xlabel("Fandango")
ax1.set_ylabel("Rotten Tomatoes")



ax2.scatter(norm_reviews["RT_user_norm"],norm_reviews["Fandango_Ratingvalue"])
ax1.set_ylabel("Fandango")
ax1.set_xlabel("Rotten Tomatoes")

Out[50]:

<matplotlib.text.Text at 0x1205ffc88>

Benchmarking correlation¶

In [51]:

import matplotlib.pyplot as plt

fig = plt.figure(figsize=(5,10))
ax1 = fig.add_subplot(3,1,1)
ax2 = fig.add_subplot(3,1,2)
ax3 = fig.add_subplot(3,1,3)


ax1.scatter(norm_reviews["Fandango_Ratingvalue"], norm_reviews["RT_user_norm"])
ax1.set_xlabel("Fandango")
ax1.set_ylabel("Rotten Tomatoes")
ax1.set_xlim(0,5)
ax1.set_ylim(0,5)


ax2.scatter(norm_reviews["Fandango_Ratingvalue"], norm_reviews["Metacritic_user_nom"])
ax2.set_xlabel("Fandango")
ax2.set_ylabel("Metacritic")
ax2.set_xlim(0,5)
ax2.set_ylim(0,5)



ax3.scatter(norm_reviews["Fandango_Ratingvalue"], norm_reviews["IMDB_norm"])
ax3.set_xlabel("Fandango")
ax3.set_ylabel("IMDB")
ax3.set_xlim(0,5)
ax3.set_ylim(0,5)

Out[51]:

(0, 5)