homework_1_for_lecture_3

import pandas as pd
url ='https://raw.githubusercontent.com/tidyverse/datascience-box/refs/heads/main/course-materials/lab-instructions/lab-03/data/nobel.csv'
df = pd.read_csv(url)
print(df.head())

   id       firstname    surname  year category  \
0   1  Wilhelm Conrad    Röntgen  1901  Physics   
1   2      Hendrik A.    Lorentz  1902  Physics   
2   3          Pieter     Zeeman  1902  Physics   
3   4           Henri  Becquerel  1903  Physics   
4   5          Pierre      Curie  1903  Physics   

                                         affiliation       city      country  \
0                                  Munich University     Munich      Germany   
1                                  Leiden University     Leiden  Netherlands   
2                               Amsterdam University  Amsterdam  Netherlands   
3                                École Polytechnique      Paris       France   
4  École municipale de physique et de chimie indu...      Paris       France   

    born_date   died_date  ... died_country_code overall_motivation share  \
0  1845-03-27  1923-02-10  ...                DE                NaN     1   
1  1853-07-18  1928-02-04  ...                NL                NaN     2   
2  1865-05-25  1943-10-09  ...                NL                NaN     2   
3  1852-12-15  1908-08-25  ...                FR                NaN     2   
4  1859-05-15  1906-04-19  ...                FR                NaN     4   

                                          motivation  born_country_original  \
0  "in recognition of the extraordinary services ...  Prussia (now Germany)   
1  "in recognition of the extraordinary service t...        the Netherlands   
2  "in recognition of the extraordinary service t...        the Netherlands   
3  "in recognition of the extraordinary services ...                 France   
4  "in recognition of the extraordinary services ...                 France   

       born_city_original died_country_original died_city_original  \
0  Lennep (now Remscheid)               Germany             Munich   
1                  Arnhem       the Netherlands                NaN   
2              Zonnemaire       the Netherlands          Amsterdam   
3                   Paris                France                NaN   
4                   Paris                France              Paris   

   city_original country_original  
0         Munich          Germany  
1         Leiden  the Netherlands  
2      Amsterdam  the Netherlands  
3          Paris           France  
4          Paris           France  

[5 rows x 26 columns]

df

	id	firstname	surname	year	category	affiliation	city	country	born_date	died_date	...	died_country_code	overall_motivation	share	motivation	born_country_original	born_city_original	died_country_original	died_city_original	city_original	country_original
0	1	Wilhelm Conrad	Röntgen	1901	Physics	Munich University	Munich	Germany	1845-03-27	1923-02-10	...	DE	NaN	1	"in recognition of the extraordinary services ...	Prussia (now Germany)	Lennep (now Remscheid)	Germany	Munich	Munich	Germany
1	2	Hendrik A.	Lorentz	1902	Physics	Leiden University	Leiden	Netherlands	1853-07-18	1928-02-04	...	NL	NaN	2	"in recognition of the extraordinary service t...	the Netherlands	Arnhem	the Netherlands	NaN	Leiden	the Netherlands
2	3	Pieter	Zeeman	1902	Physics	Amsterdam University	Amsterdam	Netherlands	1865-05-25	1943-10-09	...	NL	NaN	2	"in recognition of the extraordinary service t...	the Netherlands	Zonnemaire	the Netherlands	Amsterdam	Amsterdam	the Netherlands
3	4	Henri	Becquerel	1903	Physics	École Polytechnique	Paris	France	1852-12-15	1908-08-25	...	FR	NaN	2	"in recognition of the extraordinary services ...	France	Paris	France	NaN	Paris	France
4	5	Pierre	Curie	1903	Physics	École municipale de physique et de chimie indu...	Paris	France	1859-05-15	1906-04-19	...	FR	NaN	4	"in recognition of the extraordinary services ...	France	Paris	France	Paris	Paris	France
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
930	965	Sir Gregory P.	Winter	2018	Chemistry	MRC Laboratory of Molecular Biology	Cambridge	United Kingdom	1951-04-14	NaN	...	NaN	NaN	4	"for the phage display of peptides and antibod...	United Kingdom	Leicester	NaN	NaN	Cambridge	United Kingdom
931	966	Denis	Mukwege	2018	Peace	NaN	NaN	NaN	1955-03-01	NaN	...	NaN	NaN	2	"for their efforts to end the use of sexual vi...	Belgian Congo (now Democratic Republic of the ...	Bukavu	NaN	NaN	NaN	NaN
932	967	Nadia	Murad	2018	Peace	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	2	"for their efforts to end the use of sexual vi...	Iraq	Kojo	NaN	NaN	NaN	NaN
933	968	William D.	Nordhaus	2018	Economics	Yale University	New Haven CT	USA	1941-05-31	NaN	...	NaN	NaN	2	"for integrating climate change into long-run ...	USA	Albuquerque NM	NaN	NaN	New Haven CT	USA
934	969	Paul M.	Romer	2018	Economics	NYU Stern School of Business	New York NY	USA	NaN	NaN	...	NaN	NaN	2	"for integrating technological innovations int...	USA	Denver CO	NaN	NaN	New York NY	USA

935 rows × 26 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 935 entries, 0 to 934
Data columns (total 26 columns):
 #   Column                 Non-Null Count  Dtype 
---  ------                 --------------  ----- 
 0   id                     935 non-null    int64 
 1   firstname              935 non-null    object
 2   surname                906 non-null    object
 3   year                   935 non-null    int64 
 4   category               935 non-null    object
 5   affiliation            685 non-null    object
 6   city                   680 non-null    object
 7   country                681 non-null    object
 8   born_date              902 non-null    object
 9   died_date              627 non-null    object
 10  gender                 935 non-null    object
 11  born_city              907 non-null    object
 12  born_country           907 non-null    object
 13  born_country_code      907 non-null    object
 14  died_city              608 non-null    object
 15  died_country           614 non-null    object
 16  died_country_code      614 non-null    object
 17  overall_motivation     17 non-null     object
 18  share                  935 non-null    int64 
 19  motivation             935 non-null    object
 20  born_country_original  907 non-null    object
 21  born_city_original     907 non-null    object
 22  died_country_original  614 non-null    object
 23  died_city_original     608 non-null    object
 24  city_original          680 non-null    object
 25  country_original       681 non-null    object
dtypes: int64(3), object(23)
memory usage: 190.1+ KB

df[(df['country'].notna())]

	id	firstname	surname	year	category	affiliation	city	country	born_date	died_date	...	died_country_code	overall_motivation	share	motivation	born_country_original	born_city_original	died_country_original	died_city_original	city_original	country_original
0	1	Wilhelm Conrad	Röntgen	1901	Physics	Munich University	Munich	Germany	1845-03-27	1923-02-10	...	DE	NaN	1	"in recognition of the extraordinary services ...	Prussia (now Germany)	Lennep (now Remscheid)	Germany	Munich	Munich	Germany
1	2	Hendrik A.	Lorentz	1902	Physics	Leiden University	Leiden	Netherlands	1853-07-18	1928-02-04	...	NL	NaN	2	"in recognition of the extraordinary service t...	the Netherlands	Arnhem	the Netherlands	NaN	Leiden	the Netherlands
2	3	Pieter	Zeeman	1902	Physics	Amsterdam University	Amsterdam	Netherlands	1865-05-25	1943-10-09	...	NL	NaN	2	"in recognition of the extraordinary service t...	the Netherlands	Zonnemaire	the Netherlands	Amsterdam	Amsterdam	the Netherlands
3	4	Henri	Becquerel	1903	Physics	École Polytechnique	Paris	France	1852-12-15	1908-08-25	...	FR	NaN	2	"in recognition of the extraordinary services ...	France	Paris	France	NaN	Paris	France
4	5	Pierre	Curie	1903	Physics	École municipale de physique et de chimie indu...	Paris	France	1859-05-15	1906-04-19	...	FR	NaN	4	"in recognition of the extraordinary services ...	France	Paris	France	Paris	Paris	France
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
928	963	Frances H.	Arnold	2018	Chemistry	California Institute of Technology (Caltech)	Pasadena CA	USA	1956-07-25	NaN	...	NaN	NaN	2	"for the directed evolution of enzymes"	USA	Pittsburgh PA	NaN	NaN	Pasadena CA	USA
929	964	George P.	Smith	2018	Chemistry	University of Missouri	Columbia	USA	1941-03-10	NaN	...	NaN	NaN	4	"for the phage display of peptides and antibod...	USA	Norwalk CT	NaN	NaN	Columbia	USA
930	965	Sir Gregory P.	Winter	2018	Chemistry	MRC Laboratory of Molecular Biology	Cambridge	United Kingdom	1951-04-14	NaN	...	NaN	NaN	4	"for the phage display of peptides and antibod...	United Kingdom	Leicester	NaN	NaN	Cambridge	United Kingdom
933	968	William D.	Nordhaus	2018	Economics	Yale University	New Haven CT	USA	1941-05-31	NaN	...	NaN	NaN	2	"for integrating climate change into long-run ...	USA	Albuquerque NM	NaN	NaN	New Haven CT	USA
934	969	Paul M.	Romer	2018	Economics	NYU Stern School of Business	New York NY	USA	NaN	NaN	...	NaN	NaN	2	"for integrating technological innovations int...	USA	Denver CO	NaN	NaN	New York NY	USA

681 rows × 26 columns

df[(df['died_date'].isna())]

	id	firstname	surname	year	category	affiliation	city	country	born_date	died_date	...	died_country_code	overall_motivation	share	motivation	born_country_original	born_city_original	died_country_original	died_city_original	city_original	country_original
68	68	Chen Ning	Yang	1957	Physics	Institute for Advanced Study	Princeton NJ	USA	1922-09-22	NaN	...	NaN	NaN	2	"for their penetrating investigation of the so...	China	Hofei Anhwei	NaN	NaN	Princeton NJ	USA
69	69	Tsung-Dao	Lee	1957	Physics	Columbia University	New York NY	USA	1926-11-24	NaN	...	NaN	NaN	2	"for their penetrating investigation of the so...	China	Shanghai	NaN	NaN	New York NY	USA
94	95	Leon N.	Cooper	1972	Physics	Brown University	Providence RI	USA	1930-02-28	NaN	...	NaN	NaN	3	"for their jointly developed theory of superco...	USA	New York NY	NaN	NaN	Providence RI	USA
96	97	Leo	Esaki	1973	Physics	IBM Thomas J. Watson Research Center	Yorktown Heights NY	USA	1925-03-12	NaN	...	NaN	NaN	4	"for their experimental discoveries regarding ...	Japan	Osaka	NaN	NaN	Yorktown Heights NY	USA
97	98	Ivar	Giaever	1973	Physics	General Electric Company	Schenectady NY	USA	1929-04-05	NaN	...	NaN	NaN	4	"for their experimental discoveries regarding ...	Norway	Bergen	NaN	NaN	Schenectady NY	USA
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
930	965	Sir Gregory P.	Winter	2018	Chemistry	MRC Laboratory of Molecular Biology	Cambridge	United Kingdom	1951-04-14	NaN	...	NaN	NaN	4	"for the phage display of peptides and antibod...	United Kingdom	Leicester	NaN	NaN	Cambridge	United Kingdom
931	966	Denis	Mukwege	2018	Peace	NaN	NaN	NaN	1955-03-01	NaN	...	NaN	NaN	2	"for their efforts to end the use of sexual vi...	Belgian Congo (now Democratic Republic of the ...	Bukavu	NaN	NaN	NaN	NaN
932	967	Nadia	Murad	2018	Peace	NaN	NaN	NaN	NaN	NaN	...	NaN	NaN	2	"for their efforts to end the use of sexual vi...	Iraq	Kojo	NaN	NaN	NaN	NaN
933	968	William D.	Nordhaus	2018	Economics	Yale University	New Haven CT	USA	1941-05-31	NaN	...	NaN	NaN	2	"for integrating climate change into long-run ...	USA	Albuquerque NM	NaN	NaN	New Haven CT	USA
934	969	Paul M.	Romer	2018	Economics	NYU Stern School of Business	New York NY	USA	NaN	NaN	...	NaN	NaN	2	"for integrating technological innovations int...	USA	Denver CO	NaN	NaN	New York NY	USA

308 rows × 26 columns

Source: homework_1_for_lecture_3.ipynb

homework_2_for_lecture_3

import pandas as pd
url ='https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv'
df = pd.read_csv(url)
print(df.head())

   PassengerId  Survived  Pclass  \
0            1         0       3   
1            2         1       1   
2            3         1       3   
3            4         1       1   
4            5         0       3   

                                                Name     Sex   Age  SibSp  \
0                            Braund, Mr. Owen Harris    male  22.0      1   
1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   
2                             Heikkinen, Miss. Laina  female  26.0      0   
3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   
4                           Allen, Mr. William Henry    male  35.0      0   

   Parch            Ticket     Fare Cabin Embarked  
0      0         A/5 21171   7.2500   NaN        S  
1      0          PC 17599  71.2833   C85        C  
2      0  STON/O2. 3101282   7.9250   NaN        S  
3      0            113803  53.1000  C123        S  
4      0            373450   8.0500   NaN        S  

df

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	NaN	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	NaN	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	NaN	S
...	...	...	...	...	...	...	...	...	...	...	...	...
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	NaN	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	NaN	1	2	W./C. 6607	23.4500	NaN	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	NaN	Q

891 rows × 12 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 891 entries, 0 to 890
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  891 non-null    int64  
 1   Survived     891 non-null    int64  
 2   Pclass       891 non-null    int64  
 3   Name         891 non-null    object 
 4   Sex          891 non-null    object 
 5   Age          714 non-null    float64
 6   SibSp        891 non-null    int64  
 7   Parch        891 non-null    int64  
 8   Ticket       891 non-null    object 
 9   Fare         891 non-null    float64
 10  Cabin        204 non-null    object 
 11  Embarked     889 non-null    object 
dtypes: float64(2), int64(5), object(5)
memory usage: 83.7+ KB

from skimpy import clean_columns
df = clean_columns(df,case="snake")
print(df.columns)

Index(['passenger_id', 'survived', 'pclass', 'name', 'sex', 'age', 'sib_sp',
       'parch', 'ticket', 'fare', 'cabin', 'embarked'],
      dtype='object')

df.fillna("-")

	passenger_id	survived	pclass	name	sex	age	sib_sp	parch	ticket	fare	cabin	embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	-	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	-	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	-	S
...	...	...	...	...	...	...	...	...	...	...	...	...
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	-	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	-	1	2	W./C. 6607	23.4500	-	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	-	Q

891 rows × 12 columns

df.describe()

	passenger_id	survived	pclass	sib_sp	parch	fare
count	891.000000	891.000000	891.000000	891.000000	891.000000	891.000000
mean	446.000000	0.383838	2.308642	0.523008	0.381594	32.204208
std	257.353842	0.486592	0.836071	1.102743	0.806057	49.693429
min	1.000000	0.000000	1.000000	0.000000	0.000000	0.000000
25%	223.500000	0.000000	2.000000	0.000000	0.000000	7.910400
50%	446.000000	0.000000	3.000000	0.000000	0.000000	14.454200
75%	668.500000	1.000000	3.000000	1.000000	0.000000	31.000000
max	891.000000	1.000000	3.000000	8.000000	6.000000	512.329200

sum_table = df.describe().round(2)
sum_table

	passenger_id	survived	pclass	sib_sp	parch	fare
count	891.00	891.00	891.00	891.00	891.00	891.00
mean	446.00	0.38	2.31	0.52	0.38	32.20
std	257.35	0.49	0.84	1.10	0.81	49.69
min	1.00	0.00	1.00	0.00	0.00	0.00
25%	223.50	0.00	2.00	0.00	0.00	7.91
50%	446.00	0.00	3.00	0.00	0.00	14.45
75%	668.50	1.00	3.00	1.00	0.00	31.00
max	891.00	1.00	3.00	8.00	6.00	512.33

df.dropna()

	passenger_id	survived	pclass	name	sex	age	sib_sp	parch	ticket	fare	cabin	embarked
0	1	0	3	Braund, Mr. Owen Harris	male	22.0	1	0	A/5 21171	7.2500	-	S
1	2	1	1	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1	0	PC 17599	71.2833	C85	C
2	3	1	3	Heikkinen, Miss. Laina	female	26.0	0	0	STON/O2. 3101282	7.9250	-	S
3	4	1	1	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1	0	113803	53.1000	C123	S
4	5	0	3	Allen, Mr. William Henry	male	35.0	0	0	373450	8.0500	-	S
...	...	...	...	...	...	...	...	...	...	...	...	...
886	887	0	2	Montvila, Rev. Juozas	male	27.0	0	0	211536	13.0000	-	S
887	888	1	1	Graham, Miss. Margaret Edith	female	19.0	0	0	112053	30.0000	B42	S
888	889	0	3	Johnston, Miss. Catherine Helen "Carrie"	female	-	1	2	W./C. 6607	23.4500	-	S
889	890	1	1	Behr, Mr. Karl Howell	male	26.0	0	0	111369	30.0000	C148	C
890	891	0	3	Dooley, Mr. Patrick	male	32.0	0	0	370376	7.7500	-	Q

891 rows × 12 columns

Source: homework_2_for_lecture_3.ipynb

homework_for_lecture_2-pet_names

import pandas as pd
df = pd.read_csv('seattle_pet_licenses.csv')

df

	animal_s_name	license_issue_date	license_number	primary_breed	secondary_breed	species	zip_code
0	Ozzy	2005-03-29T00:00:00.000	130651.0	Dachshund, Standard Smooth Haired	NaN	Dog	98104
1	Jack	2009-12-23T00:00:00.000	898148.0	Schnauzer, Miniature	Terrier, Rat	Dog	98107
2	Ginger	2006-01-20T00:00:00.000	29654.0	Retriever, Golden	Retriever, Labrador	Dog	98117
3	Pepper	2006-02-07T00:00:00.000	75432.0	Manx	Mix	Cat	98103
4	Addy	2006-08-04T00:00:00.000	729899.0	Retriever, Golden	NaN	Dog	98105
...	...	...	...	...	...	...	...
66037	Lily	2016-12-27T00:00:00.000	NaN	Domestic Shorthair	Mix	Cat	98117
66038	Ellie	2016-11-29T00:00:00.000	NaN	German Shepherd	Mix	Dog	98105
66039	Sammy	2016-12-05T00:00:00.000	NaN	Terrier	Maltese	Dog	98105
66040	Buddy	2016-12-06T00:00:00.000	NaN	Bullmastiff	Mix	Dog	98105
66041	Aku	2016-12-07T00:00:00.000	NaN	Chihuahua, Short Coat	Terrier	Dog	98106

66042 rows × 7 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 66042 entries, 0 to 66041
Data columns (total 7 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   animal_s_name       64685 non-null  object 
 1   license_issue_date  66042 non-null  object 
 2   license_number      43885 non-null  float64
 3   primary_breed       66042 non-null  object 
 4   secondary_breed     22538 non-null  object 
 5   species             66042 non-null  object 
 6   zip_code            65884 non-null  object 
dtypes: float64(1), object(6)
memory usage: 3.5+ MB

df['animal_s_name'].value_counts()

animal_s_name
Lucy          566
Bella         451
Charlie       447
Max           374
Luna          361
             ... 
Manasseh        1
Taba            1
Miriam          1
Number Six      1
Rollins         1
Name: count, Length: 15795, dtype: int64

Source: homework_for_lecture_2-pet_names.ipynb

homework_for_lecture_4

import pandas as pd
df = pd.read_csv('all-ages.csv')

df

	Major_code	Major	Major_category	Total	Employed	Employed_full_time_year_round	Unemployed	Unemployment_rate	Median	P25th	P75th
0	1100	GENERAL AGRICULTURE	Agriculture & Natural Resources	128148	90245	74078	2423	0.026147	50000	34000	80000.0
1	1101	AGRICULTURE PRODUCTION AND MANAGEMENT	Agriculture & Natural Resources	95326	76865	64240	2266	0.028636	54000	36000	80000.0
2	1102	AGRICULTURAL ECONOMICS	Agriculture & Natural Resources	33955	26321	22810	821	0.030248	63000	40000	98000.0
3	1103	ANIMAL SCIENCES	Agriculture & Natural Resources	103549	81177	64937	3619	0.042679	46000	30000	72000.0
4	1104	FOOD SCIENCE	Agriculture & Natural Resources	24280	17281	12722	894	0.049188	62000	38500	90000.0
...	...	...	...	...	...	...	...	...	...	...	...
168	6211	HOSPITALITY MANAGEMENT	Business	200854	163393	122499	8862	0.051447	49000	33000	70000.0
169	6212	MANAGEMENT INFORMATION SYSTEMS AND STATISTICS	Business	156673	134478	118249	6186	0.043977	72000	50000	100000.0
170	6299	MISCELLANEOUS BUSINESS & MEDICAL ADMINISTRATION	Business	102753	77471	61603	4308	0.052679	53000	36000	83000.0
171	6402	HISTORY	Humanities & Liberal Arts	712509	478416	354163	33725	0.065851	50000	35000	80000.0
172	6403	UNITED STATES HISTORY	Humanities & Liberal Arts	17746	11887	8204	943	0.073500	50000	39000	81000.0

173 rows × 11 columns

# 按照专业分组，并把失业率从低到高升序排列
result = df.groupby(["Major"]).sum().sort_values(["Unemployment_rate"])
print(result)

                                            Major_code  \
Major                                                    
GEOLOGICAL AND GEOPHYSICAL ENGINEERING            2411   
EDUCATIONAL ADMINISTRATION AND SUPERVISION        2301   
PHARMACOLOGY                                      3607   
MATERIALS SCIENCE                                 5008   
MATHEMATICS AND COMPUTER SCIENCE                  4005   
...                                                ...   
LIBRARY SCIENCE                                   3501   
SCHOOL STUDENT COUNSELING                         2303   
MILITARY TECHNOLOGIES                             3801   
CLINICAL PSYCHOLOGY                               5202   
MISCELLANEOUS FINE ARTS                           6099   

                                                                 Major_category  \
Major                                                                             
GEOLOGICAL AND GEOPHYSICAL ENGINEERING                              Engineering   
EDUCATIONAL ADMINISTRATION AND SUPERVISION                            Education   
PHARMACOLOGY                                             Biology & Life Science   
MATERIALS SCIENCE                                                   Engineering   
MATHEMATICS AND COMPUTER SCIENCE                        Computers & Mathematics   
...                                                                         ...   
LIBRARY SCIENCE                                                       Education   
SCHOOL STUDENT COUNSELING                                             Education   
MILITARY TECHNOLOGIES                       Industrial Arts & Consumer Services   
CLINICAL PSYCHOLOGY                                    Psychology & Social Work   
MISCELLANEOUS FINE ARTS                                                    Arts   

                                            Total  Employed  \
Major                                                         
GEOLOGICAL AND GEOPHYSICAL ENGINEERING       6264      4120   
EDUCATIONAL ADMINISTRATION AND SUPERVISION   4037      3113   
PHARMACOLOGY                                 5015      3481   
MATERIALS SCIENCE                            7208      5866   
MATHEMATICS AND COMPUTER SCIENCE             7184      5874   
...                                           ...       ...   
LIBRARY SCIENCE                             16193      7091   
SCHOOL STUDENT COUNSELING                    2396      1492   
MILITARY TECHNOLOGIES                        4315      1650   
CLINICAL PSYCHOLOGY                          7638      5128   
MISCELLANEOUS FINE ARTS                      8511      6431   

                                            Employed_full_time_year_round  \
Major                                                                       
GEOLOGICAL AND GEOPHYSICAL ENGINEERING                               3350   
EDUCATIONAL ADMINISTRATION AND SUPERVISION                           2468   
PHARMACOLOGY                                                         2579   
MATERIALS SCIENCE                                                    4505   
MATHEMATICS AND COMPUTER SCIENCE                                     5039   
...                                                                   ...   
LIBRARY SCIENCE                                                      4330   
SCHOOL STUDENT COUNSELING                                            1093   
MILITARY TECHNOLOGIES                                                1708   
CLINICAL PSYCHOLOGY                                                  3297   
MISCELLANEOUS FINE ARTS                                              3802   

                                            Unemployed  Unemployment_rate  \
Major                                                                       
GEOLOGICAL AND GEOPHYSICAL ENGINEERING               0           0.000000   
EDUCATIONAL ADMINISTRATION AND SUPERVISION           0           0.000000   
PHARMACOLOGY                                        57           0.016111   
MATERIALS SCIENCE                                  134           0.022333   
MATHEMATICS AND COMPUTER SCIENCE                   150           0.024900   
...                                                ...                ...   
LIBRARY SCIENCE                                    743           0.094843   
SCHOOL STUDENT COUNSELING                          169           0.101746   
MILITARY TECHNOLOGIES                              187           0.101796   
CLINICAL PSYCHOLOGY                                587           0.102712   
MISCELLANEOUS FINE ARTS                           1190           0.156147   

                                            Median  P25th     P75th  
Major                                                                
GEOLOGICAL AND GEOPHYSICAL ENGINEERING       85000  55000  125000.0  
EDUCATIONAL ADMINISTRATION AND SUPERVISION   58000  44750   79000.0  
PHARMACOLOGY                                 60000  35000  105000.0  
MATERIALS SCIENCE                            75000  60000  100000.0  
MATHEMATICS AND COMPUTER SCIENCE             92000  53000  136000.0  
...                                            ...    ...       ...  
LIBRARY SCIENCE                              40000  30000   55000.0  
SCHOOL STUDENT COUNSELING                    41000  33200   50000.0  
MILITARY TECHNOLOGIES                        64000  39750   90000.0  
CLINICAL PSYCHOLOGY                          45000  26100   62000.0  
MISCELLANEOUS FINE ARTS                      45000  30000   60000.0  

[173 rows x 10 columns]

import pandas as pd
df = pd.read_csv('recent-grads.csv')
df

	Rank	Major_code	Major	Total	Men	Women	Major_category	ShareWomen	Sample_size	Employed	...	Part_time	Full_time_year_round	Unemployed	Unemployment_rate	Median	P25th	P75th	College_jobs	Non_college_jobs	Low_wage_jobs
0	1	2419	PETROLEUM ENGINEERING	2339.0	2057.0	282.0	Engineering	0.120564	36	1976	...	270	1207	37	0.018381	110000	95000	125000	1534	364	193
1	2	2416	MINING AND MINERAL ENGINEERING	756.0	679.0	77.0	Engineering	0.101852	7	640	...	170	388	85	0.117241	75000	55000	90000	350	257	50
2	3	2415	METALLURGICAL ENGINEERING	856.0	725.0	131.0	Engineering	0.153037	3	648	...	133	340	16	0.024096	73000	50000	105000	456	176	0
3	4	2417	NAVAL ARCHITECTURE AND MARINE ENGINEERING	1258.0	1123.0	135.0	Engineering	0.107313	16	758	...	150	692	40	0.050125	70000	43000	80000	529	102	0
4	5	2405	CHEMICAL ENGINEERING	32260.0	21239.0	11021.0	Engineering	0.341631	289	25694	...	5180	16697	1672	0.061098	65000	50000	75000	18314	4440	972
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
168	169	3609	ZOOLOGY	8409.0	3050.0	5359.0	Biology & Life Science	0.637293	47	6259	...	2190	3602	304	0.046320	26000	20000	39000	2771	2947	743
169	170	5201	EDUCATIONAL PSYCHOLOGY	2854.0	522.0	2332.0	Psychology & Social Work	0.817099	7	2125	...	572	1211	148	0.065112	25000	24000	34000	1488	615	82
170	171	5202	CLINICAL PSYCHOLOGY	2838.0	568.0	2270.0	Psychology & Social Work	0.799859	13	2101	...	648	1293	368	0.149048	25000	25000	40000	986	870	622
171	172	5203	COUNSELING PSYCHOLOGY	4626.0	931.0	3695.0	Psychology & Social Work	0.798746	21	3777	...	965	2738	214	0.053621	23400	19200	26000	2403	1245	308
172	173	3501	LIBRARY SCIENCE	1098.0	134.0	964.0	Education	0.877960	2	742	...	237	410	87	0.104946	22000	20000	22000	288	338	192

173 rows × 21 columns

# 按照专业分组，将女生占比从高到低降序排列
result = df.groupby(["Major"]).sum().sort_values(["ShareWomen"],ascending=False)
print(result)

                                               Rank  Major_code     Total  \
Major                                                                       
EARLY CHILDHOOD EDUCATION                       165        2307   37589.0   
COMMUNICATION DISORDERS SCIENCES AND SERVICES   164        6102   38279.0   
MEDICAL ASSISTING SERVICES                       52        6104   11123.0   
ELEMENTARY EDUCATION                            139        2304  170862.0   
FAMILY AND CONSUMER SCIENCES                    151        2901   58001.0   
...                                             ...         ...       ...   
MINING AND MINERAL ENGINEERING                    2        2416     756.0   
CONSTRUCTION SERVICES                            27        5601   18498.0   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES      67        2504    4790.0   
MILITARY TECHNOLOGIES                            74        3801     124.0   
FOOD SCIENCE                                     22        1104       0.0   

                                                   Men     Women  \
Major                                                              
EARLY CHILDHOOD EDUCATION                       1167.0   36422.0   
COMMUNICATION DISORDERS SCIENCES AND SERVICES   1225.0   37054.0   
MEDICAL ASSISTING SERVICES                       803.0   10320.0   
ELEMENTARY EDUCATION                           13029.0  157833.0   
FAMILY AND CONSUMER SCIENCES                    5166.0   52835.0   
...                                                ...       ...   
MINING AND MINERAL ENGINEERING                   679.0      77.0   
CONSTRUCTION SERVICES                          16820.0    1678.0   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES     4419.0     371.0   
MILITARY TECHNOLOGIES                            124.0       0.0   
FOOD SCIENCE                                       0.0       0.0   

                                                                    Major_category  \
Major                                                                                
EARLY CHILDHOOD EDUCATION                                                Education   
COMMUNICATION DISORDERS SCIENCES AND SERVICES                               Health   
MEDICAL ASSISTING SERVICES                                                  Health   
ELEMENTARY EDUCATION                                                     Education   
FAMILY AND CONSUMER SCIENCES                   Industrial Arts & Consumer Services   
...                                                                            ...   
MINING AND MINERAL ENGINEERING                                         Engineering   
CONSTRUCTION SERVICES                          Industrial Arts & Consumer Services   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES                            Engineering   
MILITARY TECHNOLOGIES                          Industrial Arts & Consumer Services   
FOOD SCIENCE                                       Agriculture & Natural Resources   

                                               ShareWomen  Sample_size  \
Major                                                                    
EARLY CHILDHOOD EDUCATION                        0.968954          342   
COMMUNICATION DISORDERS SCIENCES AND SERVICES    0.967998           95   
MEDICAL ASSISTING SERVICES                       0.927807           67   
ELEMENTARY EDUCATION                             0.923745         1629   
FAMILY AND CONSUMER SCIENCES                     0.910933          518   
...                                                   ...          ...   
MINING AND MINERAL ENGINEERING                   0.101852            7   
CONSTRUCTION SERVICES                            0.090713          295   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES      0.077453           71   
MILITARY TECHNOLOGIES                            0.000000            4   
FOOD SCIENCE                                     0.000000           36   

                                               Employed  Full_time  Part_time  \
Major                                                                           
EARLY CHILDHOOD EDUCATION                         32551      27569       7001   
COMMUNICATION DISORDERS SCIENCES AND SERVICES     29763      19975      13862   
MEDICAL ASSISTING SERVICES                         9168       5643       4107   
ELEMENTARY EDUCATION                             149339     123177      37965   
FAMILY AND CONSUMER SCIENCES                      46624      36747      15872   
...                                                 ...        ...        ...   
MINING AND MINERAL ENGINEERING                      640        556        170   
CONSTRUCTION SERVICES                             16318      15690       1751   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES        4186       4175        247   
MILITARY TECHNOLOGIES                                 0        111          0   
FOOD SCIENCE                                       3149       2558       1121   

                                               Full_time_year_round  \
Major                                                                 
EARLY CHILDHOOD EDUCATION                                     20748   
COMMUNICATION DISORDERS SCIENCES AND SERVICES                 14460   
MEDICAL ASSISTING SERVICES                                     4290   
ELEMENTARY EDUCATION                                          86540   
FAMILY AND CONSUMER SCIENCES                                  26906   
...                                                             ...   
MINING AND MINERAL ENGINEERING                                  388   
CONSTRUCTION SERVICES                                         12313   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES                    3607   
MILITARY TECHNOLOGIES                                           111   
FOOD SCIENCE                                                   1735   

                                               Unemployed  Unemployment_rate  \
Major                                                                          
EARLY CHILDHOOD EDUCATION                            1360           0.040105   
COMMUNICATION DISORDERS SCIENCES AND SERVICES        1487           0.047584   
MEDICAL ASSISTING SERVICES                            407           0.042507   
ELEMENTARY EDUCATION                                 7297           0.046586   
FAMILY AND CONSUMER SCIENCES                         3355           0.067128   
...                                                   ...                ...   
MINING AND MINERAL ENGINEERING                         85           0.117241   
CONSTRUCTION SERVICES                                1042           0.060023   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES           250           0.056357   
MILITARY TECHNOLOGIES                                   0           0.000000   
FOOD SCIENCE                                          338           0.096931   

                                               Median  P25th  P75th  \
Major                                                                 
EARLY CHILDHOOD EDUCATION                       28000  21000  35000   
COMMUNICATION DISORDERS SCIENCES AND SERVICES   28000  20000  40000   
MEDICAL ASSISTING SERVICES                      42000  30000  65000   
ELEMENTARY EDUCATION                            32000  23400  38000   
FAMILY AND CONSUMER SCIENCES                    30000  22900  40000   
...                                               ...    ...    ...   
MINING AND MINERAL ENGINEERING                  75000  55000  90000   
CONSTRUCTION SERVICES                           50000  36000  60000   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES     40000  27000  52000   
MILITARY TECHNOLOGIES                           40000  40000  40000   
FOOD SCIENCE                                    53000  32000  70000   

                                               College_jobs  Non_college_jobs  \
Major                                                                           
EARLY CHILDHOOD EDUCATION                             23515              7705   
COMMUNICATION DISORDERS SCIENCES AND SERVICES         19957              9404   
MEDICAL ASSISTING SERVICES                             2091              6948   
ELEMENTARY EDUCATION                                 108085             36972   
FAMILY AND CONSUMER SCIENCES                          20985             20133   
...                                                     ...               ...   
MINING AND MINERAL ENGINEERING                          350               257   
CONSTRUCTION SERVICES                                  3275              5351   
MECHANICAL ENGINEERING RELATED TECHNOLOGIES            1861              2121   
MILITARY TECHNOLOGIES                                     0                 0   
FOOD SCIENCE                                           1183              1274   

                                               Low_wage_jobs  
Major                                                         
EARLY CHILDHOOD EDUCATION                               2868  
COMMUNICATION DISORDERS SCIENCES AND SERVICES           5125  
MEDICAL ASSISTING SERVICES                              1270  
ELEMENTARY EDUCATION                                   11502  
FAMILY AND CONSUMER SCIENCES                            5248  
...                                                      ...  
MINING AND MINERAL ENGINEERING                            50  
CONSTRUCTION SERVICES                                    703  
MECHANICAL ENGINEERING RELATED TECHNOLOGIES              406  
MILITARY TECHNOLOGIES                                      0  
FOOD SCIENCE                                             485  

[173 rows x 20 columns]

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
a=df['Median'].groupby(df['Major_category']).sum()
a.plot.bar()
plt.show()

Source: 按照专业分组，并把失业率从低到高升序排列

homework_for_lecture_5

import pandas as pd
url ='https://raw.githubusercontent.com/tidyverse/datascience-box/refs/heads/main/course-materials/lab-instructions/lab-02/data/plastic-waste.csv'
df = pd.read_csv(url)
df

	code	entity	continent	year	gdp_per_cap	plastic_waste_per_cap	mismanaged_plastic_waste_per_cap	mismanaged_plastic_waste	coastal_pop	total_pop
0	AFG	Afghanistan	Asia	2010	1614.255001	NaN	NaN	NaN	NaN	31411743.0
1	ALB	Albania	Europe	2010	9927.181841	0.069	0.032	29705.0	2530533.0	3204284.0
2	DZA	Algeria	Africa	2010	12870.602699	0.144	0.086	520555.0	16556580.0	35468208.0
3	ASM	American Samoa	Oceania	2010	NaN	NaN	NaN	NaN	NaN	68420.0
4	AND	Andorra	Europe	2010	NaN	NaN	NaN	NaN	NaN	84864.0
...	...	...	...	...	...	...	...	...	...	...
235	VNM	Vietnam	Asia	2010	4408.168612	0.103	0.090	1833819.0	55858245.0	87848445.0
236	ESH	Western Sahara	Africa	2010	NaN	NaN	NaN	NaN	NaN	530500.0
237	YEM	Yemen	Asia	2010	4478.743599	0.103	0.077	169181.0	6048920.0	NaN
238	ZMB	Zambia	Africa	2010	3279.277161	NaN	NaN	NaN	NaN	13088570.0
239	ZWE	Zimbabwe	Africa	2010	1474.877128	NaN	NaN	NaN	NaN	12571454.0

240 rows × 10 columns

%pip install ggplot

Note: you may need to restart the kernel to use updated packages.
Collecting ggplot
  Downloading ggplot-0.11.5-py2.py3-none-any.whl.metadata (2.9 kB)
Collecting brewer2mpl (from ggplot)
  Downloading brewer2mpl-1.4.1-py2.py3-none-any.whl.metadata (3.7 kB)
Requirement already satisfied: cycler in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (0.11.0)
Requirement already satisfied: matplotlib in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (3.8.4)
Requirement already satisfied: numpy in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (1.26.4)
Requirement already satisfied: pandas in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (2.2.2)
Requirement already satisfied: patsy>=0.4 in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (0.5.6)
Requirement already satisfied: scipy in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (1.13.1)
Requirement already satisfied: six in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (1.16.0)
Requirement already satisfied: statsmodels in c:\users\shuos\anaconda3\lib\site-packages (from ggplot) (0.14.2)
Requirement already satisfied: contourpy>=1.0.1 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (1.2.0)
Requirement already satisfied: fonttools>=4.22.0 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (4.51.0)
Requirement already satisfied: kiwisolver>=1.3.1 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (1.4.4)
Requirement already satisfied: packaging>=20.0 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (23.2)
Requirement already satisfied: pillow>=8 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (10.3.0)
Requirement already satisfied: pyparsing>=2.3.1 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (3.0.9)
Requirement already satisfied: python-dateutil>=2.7 in c:\users\shuos\anaconda3\lib\site-packages (from matplotlib->ggplot) (2.9.0.post0)
Requirement already satisfied: pytz>=2020.1 in c:\users\shuos\anaconda3\lib\site-packages (from pandas->ggplot) (2024.1)
Requirement already satisfied: tzdata>=2022.7 in c:\users\shuos\anaconda3\lib\site-packages (from pandas->ggplot) (2023.3)
Downloading ggplot-0.11.5-py2.py3-none-any.whl (2.2 MB)
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
   ---------------------------------------- 0.0/2.2 MB ? eta -:--:--
    --------------------------------------- 0.0/2.2 MB 146.3 kB/s eta 0:00:15
    --------------------------------------- 0.0/2.2 MB 146.3 kB/s eta 0:00:15
    --------------------------------------- 0.0/2.2 MB 146.3 kB/s eta 0:00:15
    --------------------------------------- 0.0/2.2 MB 146.3 kB/s eta 0:00:15
    --------------------------------------- 0.0/2.2 MB 93.7 kB/s eta 0:00:24
    --------------------------------------- 0.0/2.2 MB 93.7 kB/s eta 0:00:24
   - -------------------------------------- 0.1/2.2 MB 121.3 kB/s eta 0:00:18
   - -------------------------------------- 0.1/2.2 MB 121.3 kB/s eta 0:00:18
   - -------------------------------------- 0.1/2.2 MB 121.3 kB/s eta 0:00:18
   - -------------------------------------- 0.1/2.2 MB 121.3 kB/s eta 0:00:18
   - -------------------------------------- 0.1/2.2 MB 103.4 kB/s eta 0:00:21
   - -------------------------------------- 0.1/2.2 MB 128.0 kB/s eta 0:00:17
   -- ------------------------------------- 0.1/2.2 MB 142.4 kB/s eta 0:00:15
   -- ------------------------------------- 0.1/2.2 MB 150.2 kB/s eta 0:00:14
   -- ------------------------------------- 0.1/2.2 MB 170.4 kB/s eta 0:00:13
   -- ------------------------------------- 0.2/2.2 MB 169.9 kB/s eta 0:00:13
   --- ------------------------------------ 0.2/2.2 MB 184.1 kB/s eta 0:00:12
   --- ------------------------------------ 0.2/2.2 MB 184.1 kB/s eta 0:00:12
   --- ------------------------------------ 0.2/2.2 MB 193.4 kB/s eta 0:00:11
   --- ------------------------------------ 0.2/2.2 MB 191.7 kB/s eta 0:00:11
   ---- ----------------------------------- 0.2/2.2 MB 205.4 kB/s eta 0:00:10
   ---- ----------------------------------- 0.3/2.2 MB 224.6 kB/s eta 0:00:09
   ---- ----------------------------------- 0.3/2.2 MB 224.6 kB/s eta 0:00:09
   ----- ---------------------------------- 0.3/2.2 MB 233.5 kB/s eta 0:00:09
   ----- ---------------------------------- 0.3/2.2 MB 233.5 kB/s eta 0:00:09
   ----- ---------------------------------- 0.3/2.2 MB 233.5 kB/s eta 0:00:09
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 213.2 kB/s eta 0:00:10
   ----- ---------------------------------- 0.3/2.2 MB 155.8 kB/s eta 0:00:13
   ----- ---------------------------------- 0.3/2.2 MB 157.3 kB/s eta 0:00:13
   ----- ---------------------------------- 0.3/2.2 MB 157.3 kB/s eta 0:00:13
   ------ --------------------------------- 0.3/2.2 MB 157.7 kB/s eta 0:00:12
   ------ --------------------------------- 0.4/2.2 MB 168.7 kB/s eta 0:00:11
   ------- -------------------------------- 0.4/2.2 MB 177.9 kB/s eta 0:00:11
   ------- -------------------------------- 0.4/2.2 MB 185.9 kB/s eta 0:00:10
   ------- -------------------------------- 0.4/2.2 MB 185.9 kB/s eta 0:00:10
   ------- -------------------------------- 0.4/2.2 MB 184.7 kB/s eta 0:00:10
   ------- -------------------------------- 0.4/2.2 MB 184.7 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 183.0 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 183.0 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 184.3 kB/s eta 0:00:10
   -------- ------------------------------- 0.5/2.2 MB 168.4 kB/s eta 0:00:11
   --------- ------------------------------ 0.5/2.2 MB 172.8 kB/s eta 0:00:10
   --------- ------------------------------ 0.5/2.2 MB 178.1 kB/s eta 0:00:10
   --------- ------------------------------ 0.5/2.2 MB 178.1 kB/s eta 0:00:10
   ---------- ----------------------------- 0.6/2.2 MB 181.9 kB/s eta 0:00:10
   ---------- ----------------------------- 0.6/2.2 MB 191.1 kB/s eta 0:00:09
   ----------- ---------------------------- 0.6/2.2 MB 196.3 kB/s eta 0:00:09
   ----------- ---------------------------- 0.6/2.2 MB 204.2 kB/s eta 0:00:08
   ------------ --------------------------- 0.7/2.2 MB 208.7 kB/s eta 0:00:08
   ------------ --------------------------- 0.7/2.2 MB 214.2 kB/s eta 0:00:08
   ------------ --------------------------- 0.7/2.2 MB 214.2 kB/s eta 0:00:08
   ------------ --------------------------- 0.7/2.2 MB 217.4 kB/s eta 0:00:07
   ------------ --------------------------- 0.7/2.2 MB 217.4 kB/s eta 0:00:07
   ------------ --------------------------- 0.7/2.2 MB 217.4 kB/s eta 0:00:07
   ------------ --------------------------- 0.7/2.2 MB 217.4 kB/s eta 0:00:07
   ------------- -------------------------- 0.7/2.2 MB 206.6 kB/s eta 0:00:08
   ------------- -------------------------- 0.7/2.2 MB 206.6 kB/s eta 0:00:08
   ------------- -------------------------- 0.8/2.2 MB 210.8 kB/s eta 0:00:07
   -------------- ------------------------- 0.8/2.2 MB 212.8 kB/s eta 0:00:07
   -------------- ------------------------- 0.8/2.2 MB 218.5 kB/s eta 0:00:07
   -------------- ------------------------- 0.8/2.2 MB 218.5 kB/s eta 0:00:07
   --------------- ------------------------ 0.9/2.2 MB 229.2 kB/s eta 0:00:06
   ---------------- ----------------------- 0.9/2.2 MB 229.1 kB/s eta 0:00:06
   ---------------- ----------------------- 0.9/2.2 MB 229.1 kB/s eta 0:00:06
   ---------------- ----------------------- 0.9/2.2 MB 229.1 kB/s eta 0:00:06
   ----------------- ---------------------- 1.0/2.2 MB 238.1 kB/s eta 0:00:06
   ----------------- ---------------------- 1.0/2.2 MB 238.1 kB/s eta 0:00:06
   ----------------- ---------------------- 1.0/2.2 MB 241.1 kB/s eta 0:00:06
   ------------------ --------------------- 1.0/2.2 MB 245.8 kB/s eta 0:00:05
   ------------------- -------------------- 1.1/2.2 MB 255.3 kB/s eta 0:00:05
   ------------------- -------------------- 1.1/2.2 MB 255.3 kB/s eta 0:00:05
   ------------------- -------------------- 1.1/2.2 MB 255.3 kB/s eta 0:00:05
   ------------------- -------------------- 1.1/2.2 MB 255.3 kB/s eta 0:00:05
   -------------------- ------------------- 1.1/2.2 MB 250.4 kB/s eta 0:00:05
   -------------------- ------------------- 1.1/2.2 MB 253.3 kB/s eta 0:00:05
   -------------------- ------------------- 1.1/2.2 MB 253.0 kB/s eta 0:00:05
   -------------------- ------------------- 1.1/2.2 MB 253.0 kB/s eta 0:00:05
   --------------------- ------------------ 1.2/2.2 MB 259.0 kB/s eta 0:00:04
   ---------------------- ----------------- 1.2/2.2 MB 263.0 kB/s eta 0:00:04
   ---------------------- ----------------- 1.2/2.2 MB 265.7 kB/s eta 0:00:04
   ---------------------- ----------------- 1.2/2.2 MB 265.7 kB/s eta 0:00:04
   ----------------------- ---------------- 1.3/2.2 MB 270.4 kB/s eta 0:00:04
   ----------------------- ---------------- 1.3/2.2 MB 270.8 kB/s eta 0:00:04
   ----------------------- ---------------- 1.3/2.2 MB 270.8 kB/s eta 0:00:04
   ------------------------ --------------- 1.4/2.2 MB 276.9 kB/s eta 0:00:04
   ------------------------- -------------- 1.4/2.2 MB 279.7 kB/s eta 0:00:03
   ------------------------- -------------- 1.4/2.2 MB 287.4 kB/s eta 0:00:03
   -------------------------- ------------- 1.5/2.2 MB 288.8 kB/s eta 0:00:03
   -------------------------- ------------- 1.5/2.2 MB 291.3 kB/s eta 0:00:03
   --------------------------- ------------ 1.5/2.2 MB 295.3 kB/s eta 0:00:03
   --------------------------- ------------ 1.5/2.2 MB 297.7 kB/s eta 0:00:03
   --------------------------- ------------ 1.5/2.2 MB 297.0 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.5 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.5 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 296.9 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 284.5 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 284.5 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 284.5 kB/s eta 0:00:03
   ---------------------------- ----------- 1.6/2.2 MB 284.5 kB/s eta 0:00:03
   ----------------------------- ---------- 1.6/2.2 MB 279.9 kB/s eta 0:00:03
   ----------------------------- ---------- 1.6/2.2 MB 281.1 kB/s eta 0:00:02
   ------------------------------ --------- 1.7/2.2 MB 286.9 kB/s eta 0:00:02
   ------------------------------ --------- 1.7/2.2 MB 286.9 kB/s eta 0:00:02
   ------------------------------ --------- 1.7/2.2 MB 284.8 kB/s eta 0:00:02
   ------------------------------ --------- 1.7/2.2 MB 284.8 kB/s eta 0:00:02
   ------------------------------- -------- 1.7/2.2 MB 283.8 kB/s eta 0:00:02
   ------------------------------- -------- 1.8/2.2 MB 284.2 kB/s eta 0:00:02
   ------------------------------- -------- 1.8/2.2 MB 283.7 kB/s eta 0:00:02
   -------------------------------- ------- 1.8/2.2 MB 285.6 kB/s eta 0:00:02
   -------------------------------- ------- 1.8/2.2 MB 285.6 kB/s eta 0:00:02
   -------------------------------- ------- 1.8/2.2 MB 285.6 kB/s eta 0:00:02
   -------------------------------- ------- 1.8/2.2 MB 285.6 kB/s eta 0:00:02
   --------------------------------- ------ 1.8/2.2 MB 283.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.8/2.2 MB 285.4 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   --------------------------------- ------ 1.9/2.2 MB 285.8 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 270.1 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 270.1 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 270.1 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 270.1 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 270.1 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 262.7 kB/s eta 0:00:02
   ---------------------------------- ----- 1.9/2.2 MB 264.4 kB/s eta 0:00:02
   ----------------------------------- ---- 1.9/2.2 MB 266.9 kB/s eta 0:00:01
   ----------------------------------- ---- 1.9/2.2 MB 266.9 kB/s eta 0:00:01
   ----------------------------------- ---- 1.9/2.2 MB 266.9 kB/s eta 0:00:01
   ----------------------------------- ---- 2.0/2.2 MB 265.8 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 267.1 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 266.2 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 266.2 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 266.2 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 266.2 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 264.0 kB/s eta 0:00:01
   ------------------------------------ --- 2.0/2.2 MB 264.0 kB/s eta 0:00:01
   ------------------------------------- -- 2.0/2.2 MB 262.4 kB/s eta 0:00:01
   ------------------------------------- -- 2.0/2.2 MB 262.4 kB/s eta 0:00:01
   ------------------------------------- -- 2.0/2.2 MB 262.4 kB/s eta 0:00:01
   ------------------------------------- -- 2.0/2.2 MB 262.4 kB/s eta 0:00:01
   ------------------------------------- -- 2.1/2.2 MB 258.0 kB/s eta 0:00:01
   ------------------------------------- -- 2.1/2.2 MB 259.6 kB/s eta 0:00:01
   ------------------------------------- -- 2.1/2.2 MB 258.8 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 260.4 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 243.6 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   -------------------------------------- - 2.1/2.2 MB 226.1 kB/s eta 0:00:01
   ---------------------------------------  2.2/2.2 MB 217.4 kB/s eta 0:00:01
   ---------------------------------------  2.2/2.2 MB 219.1 kB/s eta 0:00:01
   ---------------------------------------- 2.2/2.2 MB 220.0 kB/s eta 0:00:00
Downloading brewer2mpl-1.4.1-py2.py3-none-any.whl (24 kB)
Installing collected packages: brewer2mpl, ggplot
Successfully installed brewer2mpl-1.4.1 ggplot-0.11.5

import pandas as pd
from lets_plot import *

LetsPlot.setup_html()

(
    ggplot(df, aes("continent", "plastic_waste_per_cap")) +
    geom_histogram()
)

(
    ggplot(df, aes("continent", "plastic_waste_per_cap"))
    + geom_boxplot()
)

import seaborn as sns
import matplotlib.pyplot as plt

# 利用violinplot函数绘制小提琴图
sns.violinplot(x=df["continent"], y=df["plastic_waste_per_cap"])

plt.show()

(
    ggplot(df, aes("plastic_waste_per_cap", "mismanaged_plastic_waste_per_cap")) +
  geom_point()
)

(
    ggplot(df, aes("plastic_waste_per_cap", "mismanaged_plastic_waste_per_cap", colour="continent")) +
  geom_point()
)

(
ggplot(df, aes(x="total_pop", y="plastic_waste_per_cap", colour="continent")) +
  geom_point() +
  xlim(0, 150000000) +
  ylim(0, 0.8)
)

(
ggplot(df, aes(x="coastal_pop", y="plastic_waste_per_cap", colour="continent")) +
  geom_point() +
  xlim(0, 50000000) +
  ylim(0, 0.8)
)

Source: 利用violinplot函数绘制小提琴图