-
Notifications
You must be signed in to change notification settings - Fork 0
/
rq_two.py
237 lines (194 loc) · 7.74 KB
/
rq_two.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
"""
KV Le
CSE 163 AG
Final Project
A script that has multiple functions that manipulate/visualize data about
My Anime List to answer my second research question for my final project.
"""
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set()
distinct_colors = \
['#e6194b', '#3cb44b', '#ffe119', '#4363d8', '#f58231', '#911eb4',
'#46f0f0', '#f032e6', '#bcf60c', '#fabebe', '#008080', '#e6beff',
'#9a6324', '#fffac8', '#800000', '#aaffc3', '#808000', '#ffd8b1',
'#000075', '#808080', '#ffffff']
def plot_genre_count_yearly(data, top_n=15):
"""Plots the yearly count of the top_n genres
Parameters
----------
data : DataFrame
Pandas DataFrame that contains anime show data
top_n : Integer
Determines how many genres that will be placed onto the graph
Notes
-----
Visualization Type: Line Plot
File Path: plots/rq2_genres_yearly.png
If the top_n value goes over the length of "distinct_colors", the palette
will be shifted back to the default, which has indistinct colors
Top_n is determined by the overall amount of anime made with the genre
"""
yearly = data[["genre", "aired_from_year"]]
# The line below prevents 2018 b/c the data was scraped during that year,
# therefore incomplete
yearly = data[data["aired_from_year"] < 2018]
yearly = pd.concat([yearly["aired_from_year"],
pd.get_dummies(yearly["genre"]
.str.split(", ", expand=True),
prefix="", prefix_sep="")], axis=1)
yearly = yearly.groupby("aired_from_year").sum() \
.groupby(level=0, axis=1).sum().reset_index()
top_genres = data["genre"].str.split(", ", expand=True).stack() \
.str.get_dummies().sum().sort_values(ascending=False) \
.iloc[:top_n]
yearly = \
yearly.loc[:, yearly.columns.isin(list(top_genres.index)
+ ["aired_from_year"])]
palette = distinct_colors[:top_n] if top_n < len(distinct_colors) else None
fig, ax = plt.subplots()
fig.set_size_inches(15, 8)
sns.lineplot(x="aired_from_year", y="value", hue="Genre",
data=pd.melt(yearly, ["aired_from_year"])
.rename(columns={"variable": "Genre"}),
palette=palette, ax=ax)
fig.suptitle(f"Top {top_n} Genres by Year")
ax.set_xlabel("Year")
ax.set_ylabel("Amount of Anime")
ax.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0)
fig.savefig("plots/rq2_genres_yearly.png", bbox_inches="tight")
def plot_genre_score_yearly(data, top_n=10):
"""Plots the yearly score average of the top_n genres
Parameters
----------
data : DataFrame
Pandas DataFrame that contains anime show data
top_n : Integer
Determines how many genres that will be placed onto the graph
Notes
-----
Visualization Type: Line Plot
File Path: plots/rq2_genre_score_yearly.png
If the top_n value goes over the length of "distinct_colors", the palette
will be shifted back to the default, which has indistinct colors
Top_n is determined by the average scores of anime made with the genre
"""
yearly = data[["genre", "aired_from_year", "score"]].copy()
yearly["genre"] = yearly["genre"].str.split(", ")
yearly = yearly.explode("genre").groupby(["genre", "aired_from_year"]) \
.mean().reset_index()
top_genres = data[["genre", "score"]].copy()
top_genres["genre"] = top_genres["genre"].str.split(", ")
top_genres = top_genres.explode("genre").groupby("genre") \
.mean().sort_values("score", ascending=False) \
.reset_index().iloc[:top_n]
palette = distinct_colors[:top_n] if top_n < len(distinct_colors) else None
fig, ax = plt.subplots()
fig.set_size_inches(15, 8)
sns.lineplot(x="aired_from_year", y="score", hue="genre",
data=yearly[yearly["genre"].isin(top_genres["genre"])],
palette=palette, ax=ax)
fig.suptitle(f"Top {top_n} Highly Rated Genre's Average Score by Year")
ax.set_xlabel("Year")
ax.set_ylabel("Score out of Ten")
ax.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0)
fig.savefig("plots/rq2_genre_score_yearly.png", bbox_inches="tight")
plt.close(fig)
def plot_genres_multi(data, name="multi_genre", add="before 2019"):
"""Plots the amount of each genre taking into account all tags
Parameters
----------
data : DataFrame
Pandas DataFrame that contains anime show data
name : String
Determines name of the file
add: String
An addition to the title of the plot
Notes
-----
Visualization Type: Bar Plot
File Path: plots/rq2_{name}.png
"""
genres = data["genre"].str.split(", ", expand=True).stack() \
.str.get_dummies().sum().sort_values(ascending=False)
fig, ax = plt.subplots()
fig.set_size_inches(15, 10)
fig.suptitle("Amount of Animes tagged with a Genre "
f"{add} (Includes Multi-Labels)")
sns.barplot(x=genres.index, y=genres.values, ax=ax)
ax.set_xlabel("Genres")
ax.set_ylabel("Amount of Anime")
plt.xticks(rotation=45, ha="right")
fig.savefig(f"plots/rq2_{name}.png", bbox_inches="tight")
plt.close(fig)
def plot_genres_first(data, name="main_genre", add="before 2019"):
"""Plots the amount of each genre taking into account primary tags
Parameters
----------
data : DataFrame
Pandas DataFrame that contains anime show data
name : String
Determines name of the file
add: String
An addition to the title of the plot
Notes
-----
Visualization Type: Bar Plot
File Path: plots/rq2_{name}.png
"""
genres = \
data["genre"].str.split(", ", expand=True, n=1)[0].value_counts()
fig, ax = plt.subplots()
fig.set_size_inches(15, 10)
sns.barplot(x=genres.index, y=genres.values, ax=ax)
fig.suptitle(f"Amount of Animes with Main Genre {add} (First Tag)")
ax.set_xlabel("Genres")
ax.set_ylabel("Amount of Anime")
plt.xticks(rotation=45, ha="right")
fig.savefig(f"plots/rq2_{name}.png", bbox_inches="tight")
plt.close(fig)
def plot_average_scores(data):
"""Plots the score average of the anime genres
Parameters
----------
data : DataFrame
Pandas DataFrame that contains anime show data
top_n : Integer
Determines how many genres that will be placed onto the graph
Notes
-----
Visualization Type: Bar Plot
File Path: plots/rq2_average_genre_score.png
"""
info = data[["genre", "score"]].copy()
info["genre"] = info["genre"].str.split(", ")
info = info.explode("genre").groupby("genre") \
.mean().reset_index().sort_values("score", ascending=False)
fig, ax = plt.subplots()
fig.set_size_inches(16, 8)
fig.suptitle("Average Scores for a Genre")
sns.barplot(x="genre", y="score", data=info, ax=ax)
ax.set_xlabel("Genres")
ax.set_ylabel("Score out of Ten")
ax.set_ylim(6, 8)
plt.xticks(rotation=45, ha="right")
fig.savefig("plots/rq2_average_genre_score.png", bbox_inches="tight")
plt.close(fig)
def main(anime_data, data_2019):
"""
Runs all the data analysis and visualization for research question two
Parameters
----------
anime_data : DataFrame
Pandas DataFrame that contains anime show data before 2018
data_2019 : DataFrame
Pandas DataFrame that contains anime show data in 2019
"""
plot_genres_multi(anime_data)
plot_genres_first(anime_data)
plot_genres_multi(data_2019, "multi_genre2019", "in 2019")
plot_genres_first(data_2019, "main_genre2019", "in 2019")
plot_genre_count_yearly(anime_data)
plot_genre_score_yearly(anime_data)
plot_average_scores(anime_data)