# import libs
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
# read in dataset
star_wars_df = pd.read_csv("StarWars.csv", encoding="ISO-8859-1")
# drop null values from RespondentID
star_wars_df = star_wars_df.dropna(subset=["RespondentID"])
# print summary info
star_wars_df.describe(include="all")
| RespondentIDfloat64 1186 - 3292879998 | Have you seen any of the 6 films in the Star Wars franchise?object 11869.1% 3 others27.3% Missing63.6% | Do you consider yourself to be a fan of the Star Wars film franchise?object 8369.1% 3 others27.3% Missing63.6% | Which of the following Star Wars films have you seen? Please select all that apply.object 67318.2% 2 others18.2% Missing63.6% | Unnamed: 4object 57118.2% 2 others18.2% Missing63.6% | Unnamed: 5object 55018.2% 2 others18.2% Missing63.6% | Unnamed: 6object 60718.2% 2 others18.2% Missing63.6% | Unnamed: 7object 75818.2% 2 others18.2% Missing63.6% | Unnamed: 8object 73818.2% 2 others18.2% Missing63.6% | Please rank the Star Wars films in order of preference with 1 being your favorite film in the franchise and 6 being your least favorite film.object 8359.1% 3 others27.3% Missing63.6% | Unnamed: 10object 8369.1% 3 others27.3% Missing63.6% | Unnamed: 11object 618.2% 2 others18.2% Missing63.6% | Unnamed: 12object 8369.1% 3 others27.3% Missing63.6% | Unnamed: 13object 8369.1% 3 others27.3% Missing63.6% | Unnamed: 14object 8369.1% 3 others27.3% Missing63.6% | Please state whether you view the following characters favorably, unfavorably, or are unfamiliar with him/her.object 8299.1% 3 others27.3% Missing63.6% | Unnamed: 16object 8319.1% 3 others27.3% Missing63.6% | Unnamed: 17object 8319.1% 3 others27.3% Missing63.6% | Unnamed: 18object 8239.1% 3 others27.3% Missing63.6% | Unnamed: 19object 8259.1% 3 others27.3% Missing63.6% | Unnamed: 20object 8149.1% 3 others27.3% Missing63.6% | Unnamed: 21object 8269.1% 3 others27.3% Missing63.6% | Unnamed: 22object 8209.1% 3 others27.3% Missing63.6% | Unnamed: 23object 8129.1% 3 others27.3% Missing63.6% | Unnamed: 24object 8279.1% 3 others27.3% Missing63.6% | Unnamed: 25object 8309.1% 3 others27.3% Missing63.6% | Unnamed: 26object 8219.1% 3 others27.3% Missing63.6% | Unnamed: 27object 8149.1% 3 others27.3% Missing63.6% | Unnamed: 28object 8269.1% 3 others27.3% Missing63.6% | Which character shot first?object 8289.1% 3 others27.3% Missing63.6% | Are you familiar with the Expanded Universe?object 8289.1% 3 others27.3% Missing63.6% | Do you consider yourself to be a fan of the Expanded Universe?æobject 2139.1% 3 others27.3% Missing63.6% | Do you consider yourself to be a fan of the Star Trek franchise?object 10689.1% 3 others27.3% Missing63.6% | Genderobject 10469.1% 3 others27.3% Missing63.6% | Ageobject 10469.1% 3 others27.3% Missing63.6% | Household Incomeobject 8589.1% 3 others27.3% Missing63.6% | Educationobject 10369.1% 3 others27.3% Missing63.6% | Location (Census Region)object 10439.1% 3 others27.3% Missing63.6% | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
count | 1186 | 1186 | 836 | 673 | 571 | 550 | 607 | 758 | 738 | 835 | 836 | 835 | 836 | 836 | 836 | 829 | 831 | 831 | 823 | 825 | 814 | 826 | 820 | 812 | 827 | 830 | 821 | 814 | 826 | 828 | 828 | 213 | 1068 | 1046 | 1046 | 858 | 1036 | 1043 | |
unique | nan | 2 | 2 | 1 | 1 | 1 | 1 | 1 | 1 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 6 | 3 | 2 | 2 | 2 | 2 | 4 | 5 | 5 | 9 | |
top | nan | Yes | Yes | Star Wars: Episode I The Phantom Menace | Star Wars: Episode II Attack of the Clones | Star Wars: Episode III Revenge of the Sith | Star Wars: Episode IV A New Hope | Star Wars: Episode V The Empire Strikes Back | Star Wars: Episode VI Return of the Jedi | 4 | 5 | 6 | 1 | 1 | 2 | Very favorably | Very favorably | Very favorably | Somewhat favorably | Very favorably | Neither favorably nor unfavorably (neutral) | Very favorably | Neither favorably nor unfavorably (neutral) | Neither favorably nor unfavorably (neutral) | Very favorably | Very favorably | Very unfavorably | Neither favorably nor unfavorably (neutral) | Very favorably | Han | No | No | No | Female | 45-60 | $50,000 - $99,999 | Some college or Associate degree | East North Central | |
freq | nan | 936 | 552 | 673 | 571 | 550 | 607 | 758 | 738 | 237 | 300 | 217 | 204 | 289 | 232 | 610 | 552 | 547 | 269 | 591 | 213 | 310 | 236 | 248 | 474 | 562 | 204 | 207 | 605 | 325 | 615 | 114 | 641 | 549 | 291 | 298 | 328 | 181 | |
mean | 3290128200.5328836 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
| Expand rows 5 - 5 | |||||||||||||||||||||||||||||||||||||||
min | 3288372923 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
25% | 3289450962.75 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
50% | 3290147175.5 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
75% | 3290814462.5 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
max | 3292879998 | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | nan | |
| 11 rows × 38 columns | |||||||||||||||||||||||||||||||||||||||
# drop unneeded columns
star_wars_df = star_wars_df.drop(star_wars_df.columns[15:33] ,axis=1)
# convert the columns to True/False booleans
for col in ['Have you seen any of the 6 films in the Star Wars franchise?', 'Do you consider yourself to be a fan of the Star Wars film franchise?']:
star_wars_df[col] = star_wars_df[col].map({
"Yes": True,
"No": False
})
# iterate over the marked columns
for count, col in enumerate(star_wars_df.columns[3:9], start=1):
# if the value is a string holding the movie name, return True, otherwise return False
star_wars_df[col] = star_wars_df[col].apply(lambda x: True if isinstance(x, str) else False)
# rename the column
star_wars_df = star_wars_df.rename(columns={col: f"seen_movie_{count}"})
# iterate over marked column
for count, col in enumerate(star_wars_df.columns[9:15], start=1):
# convert column to float type
star_wars_df[col] = star_wars_df[col].astype(float)
# rename the column
star_wars_df = star_wars_df.rename(columns={col: f"ranking_movie_{count}"})
fans_df = star_wars_df[star_wars_df["Do you consider yourself to be a fan of the Star Wars film franchise?"] == True]
# create bar chart with ranked movies
ax = fans_df.loc[:, "ranking_movie_1":"ranking_movie_6"].mean().plot(kind="bar", figsize=(10, 5))
# set labels and title
ax.set_xlabel("Movie")
ax.set_ylabel("Ranking")
plt.title("Best Ranking Movies Among Fans")
# show plot
plt.show()
# create bar chart with most seen movies
ax = fans_df.loc[:, "seen_movie_1":"seen_movie_6"].sum().plot(kind="bar", figsize=(10, 5))
# set labels and title
ax.set_xlabel("Movie")
ax.set_ylabel("Count")
plt.title("Most Viewed Movies")
# show plot
plt.show()