Introduction to the data¶

In [36]:

import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline

pixar_movies = pd.read_csv("PixarMovies.csv")
# Number of rows
print(pixar_movies.shape[0])

In [37]:

# Number of columns
print(pixar_movies.shape[1])

In [38]:

pixar_movies.head(15)

Out[38]:

	Year Released	Movie	Length	RT Score	IMDB Score	Metacritic Score	Opening Weekend	Worldwide Gross	Domestic Gross	Adjusted Domestic Gross	International Gross	Domestic %	International %	Production Budget	Oscars Nominated	Oscars Won
0	1995	Toy Story	81	100	8.3	92	29.14	362.0	191.8	356.21	170.2	52.98%	47.02%	30	3	0
1	1998	A Bug's Life	96	92	7.2	77	33.26	363.4	162.8	277.18	200.6	44.80%	55.20%	45	1	0
2	1999	Toy Story 2	92	100	7.9	88	57.39	485.0	245.9	388.43	239.2	50.70%	49.32%	90	1	0
3	2001	Monsters, Inc.	90	96	8.1	78	62.58	528.8	255.9	366.12	272.9	48.39%	51.61%	115	3	1
4	2003	Finding Nemo	104	99	8.2	90	70.25	895.6	339.7	457.46	555.9	37.93%	62.07%	94	4	1
5	2004	The Incredibles	115	97	8.0	90	70.47	631.4	261.4	341.28	370.0	41.40%	58.60%	92	4	2
6	2006	Cars	116	74	7.2	73	60.12	462.0	244.1	302.59	217.9	52.84%	47.16%	70	2	0
7	2007	Ratatouille	111	96	8.0	96	47.00	623.7	206.4	243.65	417.3	33.09%	66.91%	150	5	1
8	2008	WALL-E	97	96	8.4	94	63.10	521.3	223.8	253.11	297.5	42.93%	57.07%	180	6	1
9	2009	Up	96	98	8.3	88	68.11	731.3	293.0	318.90	438.3	40.07%	59.93%	175	5	2
10	2010	Toy Story 3	103	99	8.4	92	110.31	1063.2	415.0	423.88	648.2	39.03%	60.97%	200	5	2
11	2011	Cars 2	113	39	6.3	57	109.00	559.9	191.5	194.43	368.4	34.20%	65.80%	200	0	0
12	2012	Brave	100	78	7.2	69	66.30	539.0	237.3	243.39	301.7	44.03%	55.97%	185	1	1
13	2013	Monsters University	107	78	7.4	65	82.43	743.6	268.5	269.59	475.1	36.11%	63.89%	200	0	0
14	2015	Inside Out	102	98	8.8	93	90.40	677.1	340.5	340.50	336.6	50.29%	49.71%	175	NaN	NaN

In [22]:

pixar_movies.dtypes

Out[22]:

Year Released                int64
Movie                       object
Length                       int64
RT Score                     int64
IMDB Score                 float64
Metacritic Score             int64
Opening Weekend            float64
Worldwide Gross            float64
Domestic Gross             float64
Adjusted Domestic Gross    float64
International Gross        float64
Domestic %                  object
International %             object
Production Budget            int64
Oscars Nominated           float64
Oscars Won                 float64
dtype: object

Data cleaning¶

In [39]:

# Use the `str` attribute followed by the string method `rstrip()` to apply the string method 
# to every value in the column.  Use the `astype()` method to cast the column to the float data type.
pixar_movies["Domestic %"] = pixar_movies["Domestic %"].str.rstrip("%").astype("float")
pixar_movies["International %"] = pixar_movies["International %"].str.rstrip("%").astype("float")

In [40]:

# Multiply the `IMDB Score` column by 10
pixar_movies["IMDB Score"] = pixar_movies["IMDB Score"]*10

In [41]:

# Create a new DataFrame containing only the first 14 rows.
filtered_pixar = pixar_movies.loc[0:13]

In [44]:

# Set the `Movie` column as the index for the DataFrame.
pixar_movies.set_index("Movie", inplace=True)
filtered_pixar.set_index("Movie", inplace=True)

In [45]:

pixar_movies

Out[45]:

	Year Released	Length	RT Score	IMDB Score	Metacritic Score	Opening Weekend	Worldwide Gross	Domestic Gross	Adjusted Domestic Gross	International Gross	Domestic %	International %	Production Budget	Oscars Nominated	Oscars Won
Movie
Toy Story	1995	81	100	83	92	29.14	362.0	191.8	356.21	170.2	52.98	47.02	30	3	0
A Bug's Life	1998	96	92	72	77	33.26	363.4	162.8	277.18	200.6	44.80	55.20	45	1	0
Toy Story 2	1999	92	100	79	88	57.39	485.0	245.9	388.43	239.2	50.70	49.32	90	1	0
Monsters, Inc.	2001	90	96	81	78	62.58	528.8	255.9	366.12	272.9	48.39	51.61	115	3	1
Finding Nemo	2003	104	99	82	90	70.25	895.6	339.7	457.46	555.9	37.93	62.07	94	4	1
The Incredibles	2004	115	97	80	90	70.47	631.4	261.4	341.28	370.0	41.40	58.60	92	4	2
Cars	2006	116	74	72	73	60.12	462.0	244.1	302.59	217.9	52.84	47.16	70	2	0
Ratatouille	2007	111	96	80	96	47.00	623.7	206.4	243.65	417.3	33.09	66.91	150	5	1
WALL-E	2008	97	96	84	94	63.10	521.3	223.8	253.11	297.5	42.93	57.07	180	6	1
Up	2009	96	98	83	88	68.11	731.3	293.0	318.90	438.3	40.07	59.93	175	5	2
Toy Story 3	2010	103	99	84	92	110.31	1063.2	415.0	423.88	648.2	39.03	60.97	200	5	2
Cars 2	2011	113	39	63	57	109.00	559.9	191.5	194.43	368.4	34.20	65.80	200	0	0
Brave	2012	100	78	72	69	66.30	539.0	237.3	243.39	301.7	44.03	55.97	185	1	1
Monsters University	2013	107	78	74	65	82.43	743.6	268.5	269.59	475.1	36.11	63.89	200	0	0
Inside Out	2015	102	98	88	93	90.40	677.1	340.5	340.50	336.6	50.29	49.71	175	NaN	NaN

Data visualization, line plots¶

In [59]:

critics_reviews = pixar_movies[["RT Score","Metacritic Score","IMDB Score"]]
critics_reviews.plot()

Out[59]:

<matplotlib.axes._subplots.AxesSubplot at 0x10eca6550>

In [60]:

critics_reviews.plot(figsize=(10,6))

Out[60]:

<matplotlib.axes._subplots.AxesSubplot at 0x10eb36630>

Data visualization, box plot¶

In [66]:

pixar_movies[["RT Score","Metacritic Score","IMDB Score"]].plot(kind="box")

Out[66]:

<matplotlib.axes._subplots.AxesSubplot at 0x10f734828>

In [68]:

pixar_movies[["RT Score","Metacritic Score","IMDB Score"]].plot(kind="box", figsize=(9,5))

Out[68]:

<matplotlib.axes._subplots.AxesSubplot at 0x10f5a7cf8>

Data visualization, stacked bar plots¶

In [96]:

revenue_proportions = filtered_pixar[["Domestic %", "International %"]]
revenue_proportions.plot(kind='bar', stacked=True, figsize=(7,6))

Out[96]:

<matplotlib.axes._subplots.AxesSubplot at 0x10e9cd080>

Next steps¶

In [65]:

# Grouped bar plot for oscar nominations / oscars won
filtered_pixar[["Oscars Nominated","Oscars Won"]].plot(kind='bar', figsize=(10,6))

Out[65]:

<matplotlib.axes._subplots.AxesSubplot at 0x10f26c400>