altair-basic
November 13, 2024
1 Cài đặt
[ ]: import warnings
[Link]('ignore')
# ẩn đi warnings
[ ]: pip install altair
Requirement already satisfied: altair in /usr/local/lib/python3.10/dist-packages
(4.2.2)
Requirement already satisfied: entrypoints in /usr/local/lib/python3.10/dist-
packages (from altair) (0.4)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages
(from altair) (3.1.4)
Requirement already satisfied: jsonschema>=3.0 in
/usr/local/lib/python3.10/dist-packages (from altair) (4.23.0)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages
(from altair) (1.26.4)
Requirement already satisfied: pandas>=0.18 in /usr/local/lib/python3.10/dist-
packages (from altair) (2.2.2)
Requirement already satisfied: toolz in /usr/local/lib/python3.10/dist-packages
(from altair) (0.12.1)
Requirement already satisfied: attrs>=22.2.0 in /usr/local/lib/python3.10/dist-
packages (from jsonschema>=3.0->altair) (24.2.0)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in
/usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair)
(2024.10.1)
Requirement already satisfied: referencing>=0.28.4 in
/usr/local/lib/python3.10/dist-packages (from jsonschema>=3.0->altair) (0.35.1)
Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-
packages (from jsonschema>=3.0->altair) (0.20.0)
Requirement already satisfied: python-dateutil>=2.8.2 in
/usr/local/lib/python3.10/dist-packages (from pandas>=0.18->altair) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-
packages (from pandas>=0.18->altair) (2024.2)
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-
packages (from pandas>=0.18->altair) (2024.2)
Requirement already satisfied: MarkupSafe>=2.0 in
1
/usr/local/lib/python3.10/dist-packages (from jinja2->altair) (3.0.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-
packages (from python-dateutil>=2.8.2->pandas>=0.18->altair) (1.16.0)
#Basic Chart
[ ]: import pandas as pd
data = [Link]({'a': list('CCCDDDEEE'),
'b': [2, 7, 4, 1, 2, 6, 8, 4, 7]})
[ ]: data
[ ]: a b
0 C 2
1 C 7
2 C 4
3 D 1
4 D 2
5 D 6
6 E 8
7 E 4
8 E 7
[ ]: import altair as alt
chart = [Link](data)
[ ]: [Link](data).mark_point()
[ ]: [Link](…)
[ ]: [Link](data).mark_point().encode(
x='a'
)
[ ]: [Link](…)
[ ]: [Link](data).mark_point().encode(
x='a',
y='b'
)
[ ]: [Link](…)
2
2 Data Transformation: Aggregation
[ ]: [Link](data).mark_point().encode(
x='a',
y='average(b)' # y là trung bình của b
)
[ ]: [Link](…)
[ ]: [Link](data).mark_bar().encode(
x='a',
y='average(b)'
)
[ ]: [Link](…)
[ ]: [Link](data).mark_bar().encode(
y='a',
x='average(b)'
)
[ ]: [Link](…)
3 Customizing your Visualization
[ ]: [Link](data).mark_bar(color='firebrick').encode(
alt.Y('a'), alt.X('average(b)') # trục y và trục x
)
[ ]: [Link](…)
4 Example
[ ]: !pip install vega_datasets
Requirement already satisfied: vega_datasets in /usr/local/lib/python3.10/dist-
packages (0.9.0)
Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages
(from vega_datasets) (2.2.2)
Requirement already satisfied: numpy>=1.22.4 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (1.26.4)
Requirement already satisfied: python-dateutil>=2.8.2 in
/usr/local/lib/python3.10/dist-packages (from pandas->vega_datasets) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (2024.2)
3
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (2024.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-
packages (from python-dateutil>=2.8.2->pandas->vega_datasets) (1.16.0)
4.1 Simple Scatter Plot with Tooltips
[ ]: import altair as alt
from vega_datasets import data
source = [Link]()
[Link](source).mark_circle(size=60).encode(
x='Horsepower',
y='Miles_per_Gallon',
color='Origin',
tooltip=['Name', 'Origin', 'Horsepower', 'Miles_per_Gallon']
).interactive()
[ ]: [Link](…)
[ ]: [Link]()
[ ]: Name Miles_per_Gallon Cylinders Displacement \
0 chevrolet chevelle malibu 18.0 8 307.0
1 buick skylark 320 15.0 8 350.0
2 plymouth satellite 18.0 8 318.0
3 amc rebel sst 16.0 8 304.0
4 ford torino 17.0 8 302.0
Horsepower Weight_in_lbs Acceleration Year Origin
0 130.0 3504 12.0 1970-01-01 USA
1 165.0 3693 11.5 1970-01-01 USA
2 150.0 3436 11.0 1970-01-01 USA
3 150.0 3433 12.0 1970-01-01 USA
4 140.0 3449 10.5 1970-01-01 USA
[ ]: [Link](source).mark_circle(size=60).encode(
x='Weight_in_lbs',
y='Miles_per_Gallon',
color='Cylinders',
tooltip=['Name','Weight_in_lbs', 'Miles_per_Gallon']
).interactive()
[ ]: [Link](…)
4
[ ]: [Link](source).mark_circle(size=60).encode(
x='Cylinders',
y='Miles_per_Gallon',
color = 'Origin',
tooltip=['Name','Miles_per_Gallon', 'Origin']
)
[ ]: [Link](…)
4.2 Simple Bar Chart
[ ]: import altair as alt
import pandas as pd
source = [Link]({
'a': ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I'],
'b': [28, 55, 43, 91, 81, 53, 19, 87, 52]
})
[Link](source).mark_bar().encode(
x='a', y='b'
).interactive()
[ ]: [Link](…)
[ ]:
4.3 Simple heat map
[ ]: import altair as alt
import numpy as np
import pandas as pd
# Compute x^2 + y^2 across a 2D grid
x, y = [Link](range(-5, 5), range(-5, 5))
z = x ** 2 + y ** 2
# Convert this grid to columnar data expected by Altair
source = [Link]({'x': [Link](),
'y': [Link](),
'z': [Link]()})
[Link](source).mark_rect().encode(
x='x:O',
y='y:O',
color='z:Q'
5
)
[ ]: [Link](…)
[ ]: import pandas as pd
import [Link] as plt
import numpy as np
fig = [Link]()
ax = fig.add_subplot(projection='3d')
# Compute x^2 + y^2 across a 2D grid
x, y = [Link](range(-50, 50), range(-50, 50))
z = x ** 2 + y ** 2
ax.plot_surface(x, y, z, cmap=[Link].YlGnBu_r)
[Link]()
4.4 Simple Histogram
[ ]: import altair as alt
from vega_datasets import data
source = [Link]
6
[Link](source).mark_bar().encode(
alt.X("IMDB_Rating:Q", bin=True),
y='count()',
)
# Vẽ mark_bar() (biểu đồ cột) với y = 'count()' -->histogram
[ ]: [Link](…)
[ ]: source
[ ]: '[Link]
[ ]: # Vẽ biểu đồ hist cho data sau:
import pandas as pd
data = {'Diem':range(11),
'Soluong':[5, 6, 8, 8, 10, 10, 20, 21, 15, 14, 10]}
df = [Link](data)
df
[ ]: Diem Soluong
0 0 5
1 1 6
2 2 8
3 3 8
4 4 10
5 5 10
6 6 20
7 7 21
8 8 15
9 9 14
10 10 10
[ ]: import altair as alt
[Link](df).mark_bar().encode(
alt.X("Diem:Q", bin=True),
y='Soluong'
)
[ ]: [Link](…)
4.5 Simple line chart
[ ]: import altair as alt
import numpy as np
import pandas as pd
7
x = [Link](100)# 0--->99
source = [Link]({
'x': x,
'f(x)': [Link](x / 5) #sin, cos, exp... -->numpy
})
[Link](source).mark_line().encode(
x='x',
y='f(x)'
)
[ ]: [Link](…)
[ ]: #Vẽ đồ thị y = sin(x)+cos(x) trong khoảng từ 0 -->10 bằng altair
import numpy as np
import altair as alt
import pandas as pd
x = range(0, 11)
y = [Link](x)+[Link](x)
df = [Link]({'x':x, 'f(x)':y})
df
[Link](df).mark_line().encode(
x='x',
y='f(x)'
)
[ ]: [Link](…)
[ ]: [Link]()
[ ]: x f(x)
0 0 0.000000
1 1 0.198669
2 2 0.389418
3 3 0.564642
4 4 0.717356
4.6 Simple Stacked Area Chart
[ ]: import altair as alt
from vega_datasets import data
source = data.iowa_electricity()
[Link](source).mark_area().encode(
8
x="year:T",
y="net_generation:Q",
color="source:N"
)
# mark_area(): biểu đồ diện tích
[ ]: [Link](…)
[ ]: source
[ ]: year source net_generation
0 2001-01-01 Fossil Fuels 35361
1 2002-01-01 Fossil Fuels 35991
2 2003-01-01 Fossil Fuels 36234
3 2004-01-01 Fossil Fuels 36205
4 2005-01-01 Fossil Fuels 36883
5 2006-01-01 Fossil Fuels 37014
6 2007-01-01 Fossil Fuels 41389
7 2008-01-01 Fossil Fuels 42734
8 2009-01-01 Fossil Fuels 38620
9 2010-01-01 Fossil Fuels 42750
10 2011-01-01 Fossil Fuels 39361
11 2012-01-01 Fossil Fuels 37379
12 2013-01-01 Fossil Fuels 34873
13 2014-01-01 Fossil Fuels 35250
14 2015-01-01 Fossil Fuels 32319
15 2016-01-01 Fossil Fuels 28437
16 2017-01-01 Fossil Fuels 29329
17 2001-01-01 Nuclear Energy 3853
18 2002-01-01 Nuclear Energy 4574
19 2003-01-01 Nuclear Energy 3988
20 2004-01-01 Nuclear Energy 4929
21 2005-01-01 Nuclear Energy 4538
22 2006-01-01 Nuclear Energy 5095
23 2007-01-01 Nuclear Energy 4519
24 2008-01-01 Nuclear Energy 5282
25 2009-01-01 Nuclear Energy 4679
26 2010-01-01 Nuclear Energy 4451
27 2011-01-01 Nuclear Energy 5215
28 2012-01-01 Nuclear Energy 4347
29 2013-01-01 Nuclear Energy 5321
30 2014-01-01 Nuclear Energy 4152
31 2015-01-01 Nuclear Energy 5243
32 2016-01-01 Nuclear Energy 4703
33 2017-01-01 Nuclear Energy 5214
34 2001-01-01 Renewables 1437
35 2002-01-01 Renewables 1963
9
36 2003-01-01 Renewables 1885
37 2004-01-01 Renewables 2102
38 2005-01-01 Renewables 2724
39 2006-01-01 Renewables 3364
40 2007-01-01 Renewables 3870
41 2008-01-01 Renewables 5070
42 2009-01-01 Renewables 8560
43 2010-01-01 Renewables 10308
44 2011-01-01 Renewables 11795
45 2012-01-01 Renewables 14949
46 2013-01-01 Renewables 16476
47 2014-01-01 Renewables 17452
48 2015-01-01 Renewables 19091
49 2016-01-01 Renewables 21241
50 2017-01-01 Renewables 21933
[ ]: data = {'Nam':[2020, 2021, 2022, 2023, 2024, 2020, 2021, 2022, 2023, 2024],
'Diem':[5, 6, 6, 8, 9, 5, 5, 7, 6, 5],
'Mon':['T', 'T', 'T', 'T', 'T', 'V', 'V', 'V', 'V', 'V']}
df = [Link](data)
df
[ ]: Nam Diem Mon
0 2020 5 T
1 2021 6 T
2 2022 6 T
3 2023 8 T
4 2024 9 T
5 2020 5 V
6 2021 5 V
7 2022 7 V
8 2023 6 V
9 2024 5 V
4.7 Simple Strip plot
[ ]: import altair as alt
from vega_datasets import data
source = [Link]()
[Link](source).mark_tick().encode(
x='Horsepower:Q',
y='Cylinders:O'
)
10
[ ]: [Link](…)
Ngoài ra, có thể tham khảo thêm ở đây: [Link]
5 IDMB data
[ ]: !pip install vega_datasets
import pandas as pd
import altair as alt
Requirement already satisfied: vega_datasets in /usr/local/lib/python3.10/dist-
packages (0.9.0)
Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages
(from vega_datasets) (2.2.2)
Requirement already satisfied: numpy>=1.22.4 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (1.26.4)
Requirement already satisfied: python-dateutil>=2.8.2 in
/usr/local/lib/python3.10/dist-packages (from pandas->vega_datasets) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (2024.2)
Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-
packages (from pandas->vega_datasets) (2024.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-
packages (from python-dateutil>=2.8.2->pandas->vega_datasets) (1.16.0)
[ ]: # Importing the Vega Dataset
from vega_datasets import data as vega_data
movies_df = pd.read_json(vega_data.[Link])
# Checking the type of data that we get
print("movies_df is of the type: ", type(movies_df))
print("movies_df: ", movies_df.shape)
movies_df is of the type: <class '[Link]'>
movies_df: (3201, 16)
[ ]: movies_df.head(5)
[ ]: Title US_Gross Worldwide_Gross US_DVD_Sales \
0 The Land Girls 146083.0 146083.0 NaN
1 First Love, Last Rites 10876.0 10876.0 NaN
2 I Married a Strange Person 203134.0 203134.0 NaN
3 Let's Talk About Sex 373615.0 373615.0 NaN
4 Slam 1009819.0 1087521.0 NaN
11
Production_Budget Release_Date MPAA_Rating Running_Time_min Distributor \
0 8000000.0 Jun 12 1998 R NaN Gramercy
1 300000.0 Aug 07 1998 R NaN Strand
2 250000.0 Aug 28 1998 None NaN Lionsgate
3 300000.0 Sep 11 1998 None NaN Fine Line
4 1000000.0 Oct 09 1998 R NaN Trimark
Source Major_Genre Creative_Type Director \
0 None None None None
1 None Drama None None
2 None Comedy None None
3 None Comedy None None
4 Original Screenplay Drama Contemporary Fiction None
Rotten_Tomatoes_Rating IMDB_Rating IMDB_Votes
0 NaN 6.1 1071.0
1 NaN 6.9 207.0
2 NaN 6.8 865.0
3 13.0 NaN NaN
4 62.0 3.4 165.0
[ ]: movies_df.columns #Tên các columns (tên biến - cột)
[ ]: Index(['Title', 'US_Gross', 'Worldwide_Gross', 'US_DVD_Sales',
'Production_Budget', 'Release_Date', 'MPAA_Rating', 'Running_Time_min',
'Distributor', 'Source', 'Major_Genre', 'Creative_Type', 'Director',
'Rotten_Tomatoes_Rating', 'IMDB_Rating', 'IMDB_Votes'],
dtype='object')
[ ]: def extract_year(value):
return pd.to_datetime(value, format='%b %d %Y').year
# chỉ lấy ra year của cột Release_Date --> convert sang datetime
movies_df["Year"] = movies_df["Release_Date"].apply(extract_year)
[ ]: movies_df.columns
[ ]: Index(['Title', 'US_Gross', 'Worldwide_Gross', 'US_DVD_Sales',
'Production_Budget', 'Release_Date', 'MPAA_Rating', 'Running_Time_min',
'Distributor', 'Source', 'Major_Genre', 'Creative_Type', 'Director',
'Rotten_Tomatoes_Rating', 'IMDB_Rating', 'IMDB_Votes', 'Year'],
dtype='object')
[ ]: movies_df.head()
12
[ ]: Title US_Gross Worldwide_Gross US_DVD_Sales \
0 The Land Girls 146083.0 146083.0 NaN
1 First Love, Last Rites 10876.0 10876.0 NaN
2 I Married a Strange Person 203134.0 203134.0 NaN
3 Let's Talk About Sex 373615.0 373615.0 NaN
4 Slam 1009819.0 1087521.0 NaN
Production_Budget Release_Date MPAA_Rating Running_Time_min Distributor \
0 8000000.0 Jun 12 1998 R NaN Gramercy
1 300000.0 Aug 07 1998 R NaN Strand
2 250000.0 Aug 28 1998 None NaN Lionsgate
3 300000.0 Sep 11 1998 None NaN Fine Line
4 1000000.0 Oct 09 1998 R NaN Trimark
Source Major_Genre Creative_Type Director \
0 None None None None
1 None Drama None None
2 None Comedy None None
3 None Comedy None None
4 Original Screenplay Drama Contemporary Fiction None
Rotten_Tomatoes_Rating IMDB_Rating IMDB_Votes Year
0 NaN 6.1 1071.0 1998
1 NaN 6.9 207.0 1998
2 NaN 6.8 865.0 1998
3 13.0 NaN NaN 1998
4 62.0 3.4 165.0 1998
[ ]: movies_df["Year"].value_counts()
[ ]: Year
2006 220
2005 210
2002 208
2004 192
2000 188
…
1929 1
2020 1
1946 1
2043 1
1943 1
Name: count, Length: 91, dtype: int64
[ ]: movies_2000 = movies_df[movies_df["Year"] == 2000]
movies_2000.shape
13
[ ]: (188, 17)
5.1 Chart
[ ]: [Link](movies_2000).mark_point().encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross')
)
[ ]: [Link](…)
[ ]: [Link](movies_2000).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
[Link]('US_Gross')
)
[ ]: [Link](…)
[ ]: [Link](movies_2000).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
[Link]('US_Gross'),
[Link]('Major_Genre'),
[Link](0.7)
)
[ ]: [Link](…)
[ ]: [Link](movies_2000).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
[Link]('US_Gross'),
[Link]('Major_Genre'),
[Link](0.7),
tooltip = [[Link]('Title'),
[Link]('Production_Budget'),
[Link]('Worldwide_Gross'),
[Link]('US_Gross')
]
)
[ ]: [Link](…)
[ ]: [Link](movies_2000).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
14
[Link]('US_Gross'),
[Link]('Major_Genre'),
[Link](0.7),
tooltip = [[Link]('Title'),
[Link]('Production_Budget'),
[Link]('Worldwide_Gross'),
[Link]('US_Gross')
]
).interactive()
[ ]: [Link](…)
[ ]: select_year = alt.selection_single(
name='Select', fields=['Year'], init={'Year': 1928},
bind=alt.binding_range(min=1928, max=2046, step=10)
)
[Link](movies_df).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
[Link]('US_Gross'),
[Link]('Major_Genre'),
[Link](0.7),
tooltip = [[Link]('Title:N'),
[Link]('Production_Budget:Q'),
[Link]('Worldwide_Gross:Q'),
[Link]('US_Gross:Q')
]
).add_selection(select_year).transform_filter(select_year)
[ ]: [Link](…)
[ ]: select_year = alt.selection_single(
name='Select', fields=['Year'], init={'Year': 1968},
bind=alt.binding_range(min=1968, max=2008, step= 1)
)
[Link](movies_df).mark_point(filled=True).encode(
alt.X('Production_Budget'),
alt.Y('Worldwide_Gross'),
[Link]('US_Gross'),
[Link]('Major_Genre'),
[Link](0.7),
tooltip = [[Link]('Title:N'),
[Link]('Production_Budget:Q'),
[Link]('Worldwide_Gross:Q'),
[Link]('US_Gross:Q')
15
]
).add_selection(select_year).transform_filter(select_year)
[ ]: [Link](…)
16