import pandas as pd
reviews = pd.read_csv('fandango_scores.csv')
cols = ['FILM','RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
norm_reviews = reviews[cols]
print(norm_reviews)
FILM RT_user_norm
0 Avengers: Age of Ultron (2015) 4.30
1 Cinderella (2015) 4.00
2 Ant-Man (2015) 4.50
3 Do You Believe? (2015) 4.20
4 Hot Tub Time Machine 2 (2015) 1.40
5 The Water Diviner (2015) 3.10
6 Irrational Man (2015) 2.65
7 Top Five (2014) 3.20
8 Shaun the Sheep Movie (2015) 4.10
9 Love & Mercy (2015) 4.35
10 Far From The Madding Crowd (2015) 3.85
11 Black Sea (2015) 3.00
12 Leviathan (2014) 3.95
13 Unbroken (2014) 3.50
14 The Imitation Game (2014) 4.60
15 Taken 3 (2015) 2.30
16 Ted 2 (2015) 2.90
17 Southpaw (2015) 4.00
18 Night at the Museum: Secret of the Tomb (2014) 2.90
19 Pixels (2015) 2.70
20 McFarland, USA (2015) 4.45
21 Insidious: Chapter 3 (2015) 2.80
22 The Man From U.N.C.L.E. (2015) 4.00
23 Run All Night (2015) 2.95
24 Trainwreck (2015) 3.70
25 Selma (2014) 4.30
26 Ex Machina (2015) 4.30
27 Still Alice (2015) 4.25
28 Wild Tales (2014) 4.60
29 The End of the Tour (2015) 4.45
.. ... ...
116 Clouds of Sils Maria (2015) 3.35
117 Testament of Youth (2015) 3.95
118 Infinitely Polar Bear (2015) 3.80
119 Phoenix (2015) 4.05
120 The Wolfpack (2015) 3.65
121 The Stanford Prison Experiment (2015) 4.35
122 Tangerine (2015) 4.30
123 Magic Mike XXL (2015) 3.20
124 Home (2015) 3.25
125 The Wedding Ringer (2015) 3.30
126 Woman in Gold (2015) 4.05
127 The Last Five Years (2015) 3.00
128 Mission: Impossible – Rogue Nation (2015) 4.50
129 Amy (2015) 4.55
130 Jurassic World (2015) 4.05
131 Minions (2015) 2.60
132 Max (2015) 3.65
133 Paul Blart: Mall Cop 2 (2015) 1.80
134 The Longest Ride (2015) 3.65
135 The Lazarus Effect (2015) 1.15
136 The Woman In Black 2 Angel of Death (2015) 1.25
137 Danny Collins (2015) 3.75
138 Spare Parts (2015) 4.15
139 Serena (2015) 1.25
140 Inside Out (2015) 4.50
141 Mr. Holmes (2015) 3.90
142 '71 (2015) 4.10
143 Two Days, One Night (2014) 3.90
144 Gett: The Trial of Viviane Amsalem (2015) 4.05
145 Kumiko, The Treasure Hunter (2015) 3.15
Metacritic_user_nom IMDB_norm Fandango_Ratingvalue Fandango_Stars
0 3.55 3.90 4.5 5.0
1 3.75 3.55 4.5 5.0
2 4.05 3.90 4.5 5.0
3 2.35 2.70 4.5 5.0
4 1.70 2.55 3.0 3.5
5 3.40 3.60 4.0 4.5
6 3.80 3.45 3.5 4.0
7 3.40 3.25 3.5 4.0
8 4.40 3.70 4.0 4.5
9 4.25 3.90 4.0 4.5
10 3.75 3.60 4.0 4.5
11 3.30 3.20 3.5 4.0
12 3.60 3.85 3.5 4.0
13 3.25 3.60 4.1 4.5
14 4.10 4.05 4.6 5.0
15 2.30 3.05 4.1 4.5
16 3.25 3.30 4.1 4.5
17 4.10 3.90 4.6 5.0
18 2.90 3.15 4.1 4.5
19 2.65 2.80 4.1 4.5
20 3.60 3.75 4.6 5.0
21 3.45 3.15 4.1 4.5
22 3.95 3.80 4.1 4.5
23 3.65 3.30 4.1 4.5
24 3.00 3.35 4.1 4.5
25 3.55 3.75 4.6 5.0
26 3.95 3.85 4.1 4.5
27 3.90 3.75 4.1 4.5
28 4.40 4.10 4.1 4.5
29 3.75 3.95 4.1 4.5
.. ... ... ... ...
116 3.55 3.40 3.4 3.5
117 3.95 3.65 3.9 4.0
118 3.95 3.60 3.9 4.0
119 4.00 3.60 3.4 3.5
120 3.50 3.55 3.4 3.5
121 4.25 3.55 3.9 4.0
122 3.65 3.70 3.9 4.0
123 2.70 3.15 4.4 4.5
124 3.65 3.35 4.4 4.5
125 1.65 3.35 4.4 4.5
126 3.60 3.70 4.4 4.5
127 3.45 3.00 4.4 4.5
128 4.00 3.90 4.4 4.5
129 4.40 4.00 4.4 4.5
130 3.50 3.65 4.5 4.5
131 2.85 3.35 4.0 4.0
132 2.95 3.50 4.5 4.5
133 1.20 2.15 3.5 3.5
134 2.40 3.60 4.5 4.5
135 2.45 2.60 3.0 3.0
136 2.20 2.45 3.0 3.0
137 3.55 3.55 4.0 4.0
138 3.55 3.60 4.5 4.5
139 2.65 2.70 3.0 3.0
140 4.45 4.30 4.5 4.5
141 3.95 3.70 4.0 4.0
142 3.75 3.60 3.5 3.5
143 4.40 3.70 3.5 3.5
144 3.65 3.90 3.5 3.5
145 3.20 3.35 3.5 3.5
[146 rows x 6 columns]
import matplotlib.pyplot as plt
from numpy import arange
# The Axes.bar() method has 2 required parameters, left and height.
# We use the left parameter to specify the x coordinates of the left sides of the bar.
# We use the height parameter to specify the height of each bar
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.loc[0,num_cols].values
print(bar_heights)
bar_positions = arange(5)+0.75
print(bar_positions)
fig, ax = plt.subplots()
ax.bar(bar_positions,bar_heights,0.5)
plt.show()
[4.3 3.55 3.9 4.5 5.0]
[0.75 1.75 2.75 3.75 4.75]
# By default, matplotlib sets the x-axis tick labels to the integer values the bars
# spanned on the x-axis (from 0 to 6). We only need tick labels on the x-axis where the bars are positioned.
# We can use Axes.set_xticks() to change the positions of the ticks to [1, 2, 3, 4, 5]:
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_heights = norm_reviews.loc[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
print(tick_positions)
fig, ax = plt.subplots()
ax.bar(bar_positions,bar_heights,0.5)
ax.set_xticks(tick_positions)
ax.set_xticklabels(num_cols,rotation=45)
ax.set_xlabel('Rating Source')
ax.set_ylabel('Average Rating')
ax.set_title('Average User Rating For Avengers: Age of Ultron (2015)')
plt.show()
range(1, 6)
import matplotlib.pyplot as plt
from numpy import arange
num_cols = ['RT_user_norm', 'Metacritic_user_nom', 'IMDB_norm', 'Fandango_Ratingvalue', 'Fandango_Stars']
bar_widths = norm_reviews.loc[0, num_cols].values
bar_positions = arange(5) + 0.75
tick_positions = range(1,6)
fig, ax = plt.subplots()
ax.barh(bar_positions, bar_widths, 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()
# Let's look at a plot that can help us visualize many points
fig, ax = plt.subplots()
ax.scatter(norm_reviews['Fandango_Ratingvalue'],norm_reviews['RT_user_norm'])
ax.set_xlabel('Fandango')
ax.set_ylabel('Rotten Tomatoes')
plt.show()
# Switching Axes
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'])
ax2.set_xlabel('Rotten Tomatoes')
ax2.set_ylabel('Fandango')
plt.show()
