This package contains similar packages to the sample ones we automatically find installed within R studio. This link contains more packages with sample data sets: https://towardsdatascience.com/datasets-in-python-425475a20eb1
import seaborn as sns
## list datasets in the seaborn package
print(sns.get_dataset_names())['anagrams', 'anscombe', 'attention', 'brain_networks', 'car_crashes', 'diamonds', 'dots', 'dowjones', 'exercise', 'flights', 'fmri', 'geyser', 'glue', 'healthexp', 'iris', 'mpg', 'penguins', 'planets', 'seaice', 'taxis', 'tips', 'titanic']### First lets import all the different libraries we will be using
# people say this is comparable to the tidyverse
import pandas as pd
# similar to ggplot
import plotnine as pn
# plots with js elements
import plotly.express as px
# syntax similar to matlab
import matplotlib.pyplot as matplt
# plots that allow the user to import from the rendered markdown
import altair as altr
# Import diamonds dataset
diamonds = sns.load_dataset('diamonds')
diamonds.info()<class 'pandas.core.frame.DataFrame'>
RangeIndex: 53940 entries, 0 to 53939
Data columns (total 10 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 carat 53940 non-null float64
1 cut 53940 non-null category
2 color 53940 non-null category
3 clarity 53940 non-null category
4 depth 53940 non-null float64
5 table 53940 non-null float64
6 price 53940 non-null int64
7 x 53940 non-null float64
8 y 53940 non-null float64
9 z 53940 non-null float64
dtypes: category(3), float64(6), int64(1)
memory usage: 3.0 MBThis package is just like the ggplot2 package, one thing to note that instead of data = cars we see the ggplot(cars). In this case data = cars will give us an error
## Plotnine which is equivalent to ggplot
(pn.ggplot(diamonds) +
pn.aes(x='cut') +
pn.geom_bar(size=20) +
pn.coord_flip() +
pn.ggtitle('Number of Diamonds by Cut')
)
<Figure Size: (640 x 480)>## Plotly
px.histogram(
diamonds,
y = "cut",
title= "Number of Diamonds by Cut"
)My only issue is that I have not figure out how to make her a bigger size within a markdown document. Additionally altair can’t deal with data having more than 5000 rows
## Altair
(
altr.Chart(
diamonds.sample(5000),
title = "Number of Diamonds by Cut"
)
.mark_bar()
.encode(
x = 'count()', y = altr.Y('cut')
)
)(diamonds.sample(1000)['carat']
.plot
.hist(bins=20))<Axes: ylabel='Frequency'>
matplt.hist('carat', bins = 20, data = diamonds.sample(1000))(array([208., 157., 113., 118., 68., 110., 56., 48., 7., 48., 19.,
1., 23., 16., 3., 1., 1., 1., 0., 2.]),
array([0.23 , 0.369, 0.508, 0.647, 0.786, 0.925, 1.064, 1.203, 1.342,
1.481, 1.62 , 1.759, 1.898, 2.037, 2.176, 2.315, 2.454, 2.593,
2.732, 2.871, 3.01 ]),
<BarContainer object of 20 artists>)
(pn.ggplot(diamonds.sample(1000)) +
pn.aes(x = 'carat') +
pn.geom_histogram(binwidth = 0.1) +
pn.xlim(0,3)
)C:\Users\hanna\AppData\Local\Programs\Python\Python311\Lib\site-packages\plotnine\layer.py:284: PlotnineWarning: stat_bin : Removed 1 rows containing non-finite values.
C:\Users\hanna\AppData\Local\Programs\Python\Python311\Lib\site-packages\plotnine\layer.py:364: PlotnineWarning: geom_histogram : Removed 2 rows containing missing values.
<Figure Size: (640 x 480)>px.histogram(
diamonds.sample(1000), x = 'carat'
)(
altr.Chart(diamonds.sample(1000))
.mark_bar()
.encode(
altr.X('carat', bin = altr.Bin(step = 0.1)),
y = 'count()'
)
)(
diamonds.sample(1000)
.plot
.scatter(x = 'carat', y = 'price')
.set(
title = 'Carat vs Diamond Price',
xlabel = 'Diamond Carat',
ylabel = 'Diamond Price'
)
)[Text(0.5, 1.0, 'Carat vs Diamond Price'),
Text(0.5, 0, 'Diamond Carat'),
Text(0, 0.5, 'Diamond Price')]
(
pn.ggplot(diamonds.sample(1000)) +
pn.aes(x = 'carat', y = 'price') +
pn.geom_point() +
pn.ggtitle('Carat vs Diamond Price') +
pn.xlab('Diamond Carat')+
pn.ylab('Diamond Price')
)
<Figure Size: (640 x 480)>px.scatter(
diamonds.sample(1000),
x = 'carat',
y = 'price',
title = 'Diamond Carat vs Price',
labels = dict(carat = 'Diamond Carat', price = 'Diamond Price')
)altr.Chart(diamonds.sample(1000)).mark_circle().encode(
altr.X(
'carat',
title='Diamond Carat',
),
altr.Y(
'price',
title='Diamond Price',
),
).properties(
title='Diamond Carat vs Diamond Price'
)