straw/pm21-dragon
1
2
Fork 23
Code Issues Pull requests Actions Packages Projects Releases Wiki Activity
pm21-dragon/lectures/lecture-06/2 - Pandas.ipynb
Andrew Straw eb5db8a689 lecture as finished
2024-11-25 07:21:30 +01:00

241 KiB
Raw Blame History

None <html> <head> </head>

Pandas

pandas logo

"high-performance, easy-to-use data structures and data analysis tools" https://pandas.pydata.org/

Pandas is typically imported as pd.

In [1]:
import pandas as pd
In [8]:
# We will start with the Iris dataset from a previous lecture
iris_dataset = {'sepal length (cm)': [5.1, 4.9, 4.7, 4.6, 5.0, 5.4, 4.6, 5.0, 4.4, 4.9, 5.4, 4.8, 4.8, 4.3, 5.8, 5.7, 5.4, 5.1, 5.7, 5.1, 5.4, 5.1, 4.6, 5.1, 4.8, 5.0, 5.0, 5.2, 5.2, 4.7, 4.8, 5.4, 5.2, 5.5, 4.9, 5.0, 5.5, 4.9, 4.4, 5.1, 5.0, 4.5, 4.4, 5.0, 5.1, 4.8, 5.1, 4.6, 5.3, 5.0, 7.0, 6.4, 6.9, 5.5, 6.5, 5.7, 6.3, 4.9, 6.6, 5.2, 5.0, 5.9, 6.0, 6.1, 5.6, 6.7, 5.6, 5.8, 6.2, 5.6, 5.9, 6.1, 6.3, 6.1, 6.4, 6.6, 6.8, 6.7, 6.0, 5.7, 5.5, 5.5, 5.8, 6.0, 5.4, 6.0, 6.7, 6.3, 5.6, 5.5, 5.5, 6.1, 5.8, 5.0, 5.6, 5.7, 5.7, 6.2, 5.1, 5.7, 6.3, 5.8, 7.1, 6.3, 6.5, 7.6, 4.9, 7.3, 6.7, 7.2, 6.5, 6.4, 6.8, 5.7, 5.8, 6.4, 6.5, 7.7, 7.7, 6.0, 6.9, 5.6, 7.7, 6.3, 6.7, 7.2, 6.2, 6.1, 6.4, 7.2, 7.4, 7.9, 6.4, 6.3, 6.1, 7.7, 6.3, 6.4, 6.0, 6.9, 6.7, 6.9, 5.8, 6.8, 6.7, 6.7, 6.3, 6.5, 6.2, 5.9], 'sepal width (cm)': [3.5, 3.0, 3.2, 3.1, 3.6, 3.9, 3.4, 3.4, 2.9, 3.1, 3.7, 3.4, 3.0, 3.0, 4.0, 4.4, 3.9, 3.5, 3.8, 3.8, 3.4, 3.7, 3.6, 3.3, 3.4, 3.0, 3.4, 3.5, 3.4, 3.2, 3.1, 3.4, 4.1, 4.2, 3.1, 3.2, 3.5, 3.6, 3.0, 3.4, 3.5, 2.3, 3.2, 3.5, 3.8, 3.0, 3.8, 3.2, 3.7, 3.3, 3.2, 3.2, 3.1, 2.3, 2.8, 2.8, 3.3, 2.4, 2.9, 2.7, 2.0, 3.0, 2.2, 2.9, 2.9, 3.1, 3.0, 2.7, 2.2, 2.5, 3.2, 2.8, 2.5, 2.8, 2.9, 3.0, 2.8, 3.0, 2.9, 2.6, 2.4, 2.4, 2.7, 2.7, 3.0, 3.4, 3.1, 2.3, 3.0, 2.5, 2.6, 3.0, 2.6, 2.3, 2.7, 3.0, 2.9, 2.9, 2.5, 2.8, 3.3, 2.7, 3.0, 2.9, 3.0, 3.0, 2.5, 2.9, 2.5, 3.6, 3.2, 2.7, 3.0, 2.5, 2.8, 3.2, 3.0, 3.8, 2.6, 2.2, 3.2, 2.8, 2.8, 2.7, 3.3, 3.2, 2.8, 3.0, 2.8, 3.0, 2.8, 3.8, 2.8, 2.8, 2.6, 3.0, 3.4, 3.1, 3.0, 3.1, 3.1, 3.1, 2.7, 3.2, 3.3, 3.0, 2.5, 3.0, 3.4, 3.0], 'petal length (cm)': [1.4, 1.4, 1.3, 1.5, 1.4, 1.7, 1.4, 1.5, 1.4, 1.5, 1.5, 1.6, 1.4, 1.1, 1.2, 1.5, 1.3, 1.4, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.9, 1.6, 1.6, 1.5, 1.4, 1.6, 1.6, 1.5, 1.5, 1.4, 1.5, 1.2, 1.3, 1.4, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6, 1.9, 1.4, 1.6, 1.4, 1.5, 1.4, 4.7, 4.5, 4.9, 4.0, 4.6, 4.5, 4.7, 3.3, 4.6, 3.9, 3.5, 4.2, 4.0, 4.7, 3.6, 4.4, 4.5, 4.1, 4.5, 3.9, 4.8, 4.0, 4.9, 4.7, 4.3, 4.4, 4.8, 5.0, 4.5, 3.5, 3.8, 3.7, 3.9, 5.1, 4.5, 4.5, 4.7, 4.4, 4.1, 4.0, 4.4, 4.6, 4.0, 3.3, 4.2, 4.2, 4.2, 4.3, 3.0, 4.1, 6.0, 5.1, 5.9, 5.6, 5.8, 6.6, 4.5, 6.3, 5.8, 6.1, 5.1, 5.3, 5.5, 5.0, 5.1, 5.3, 5.5, 6.7, 6.9, 5.0, 5.7, 4.9, 6.7, 4.9, 5.7, 6.0, 4.8, 4.9, 5.6, 5.8, 6.1, 6.4, 5.6, 5.1, 5.6, 6.1, 5.6, 5.5, 4.8, 5.4, 5.6, 5.1, 5.1, 5.9, 5.7, 5.2, 5.0, 5.2, 5.4, 5.1], 'petal width (cm)': [0.2, 0.2, 0.2, 0.2, 0.2, 0.4, 0.3, 0.2, 0.2, 0.1, 0.2, 0.2, 0.1, 0.1, 0.2, 0.4, 0.4, 0.3, 0.3, 0.3, 0.2, 0.4, 0.2, 0.5, 0.2, 0.2, 0.4, 0.2, 0.2, 0.2, 0.2, 0.4, 0.1, 0.2, 0.2, 0.2, 0.2, 0.1, 0.2, 0.2, 0.3, 0.3, 0.2, 0.6, 0.4, 0.3, 0.2, 0.2, 0.2, 0.2, 1.4, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6, 1.0, 1.3, 1.4, 1.0, 1.5, 1.0, 1.4, 1.3, 1.4, 1.5, 1.0, 1.5, 1.1, 1.8, 1.3, 1.5, 1.2, 1.3, 1.4, 1.4, 1.7, 1.5, 1.0, 1.1, 1.0, 1.2, 1.6, 1.5, 1.6, 1.5, 1.3, 1.3, 1.3, 1.2, 1.4, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1, 1.3, 2.5, 1.9, 2.1, 1.8, 2.2, 2.1, 1.7, 1.8, 1.8, 2.5, 2.0, 1.9, 2.1, 2.0, 2.4, 2.3, 1.8, 2.2, 2.3, 1.5, 2.3, 2.0, 2.0, 1.8, 2.1, 1.8, 1.8, 1.8, 2.1, 1.6, 1.9, 2.0, 2.2, 1.5, 1.4, 2.3, 2.4, 1.8, 1.8, 2.1, 2.4, 2.3, 1.9, 2.3, 2.5, 2.3, 1.9, 2.0, 2.3, 1.8], 'species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica']}

pandas DataFrame

The primary interest in pandas is the DataFrame. A DataFrame is a type, conceptually related to a numpy array, for containing large amounts of data and operating efficiently on it. With DataFrames, however, there is typically more structure. A DataFrame is always two dimensional, with every element in a column having the same data type. There are multiple columns, each with a name and potentially different datatypes. The easiest way to think about a DataFrame is like a well-organized spreadsheet. Indeed, DataFrames are great for doing the kind of calculations you might do in spreadsheets.

Creation

One way to create a pandas DataFrame is by using its constructor, DataFrame(). If provided one argument, a dictionary, it will create a new DataFrame instance with a column from each item in the dict. The dict key becomes the column name and the dict value (a Python sequence) becomes are the column data values. Pandas will infer the datatype for the column. It is required that the length of all sequences in the dict are identical so that each column in the DataFrame has the same length.

As an example, let's load our Iris dataset.

In [9]:
df = pd.DataFrame(iris_dataset)
In [10]:
df
Out[10]:
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
... ... ... ... ... ...
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica

150 rows × 5 columns

The head() and tail() methods both return dataframes which are a subset of the original dataframe, with the top and bottom rows, respectively:

In [11]:
df.head()
Out[11]:
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
In [12]:
df.tail()
Out[12]:
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica

Note that jupyter and pandas work nicely together to give the nicely formatted output you see above. Here is plain print():

In [13]:
print(df.tail())

     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \
145                6.7               3.0                5.2               2.3   
146                6.3               2.5                5.0               1.9   
147                6.5               3.0                5.2               2.0   
148                6.2               3.4                5.4               2.3   
149                5.9               3.0                5.1               1.8   

       species  
145  virginica  
146  virginica  
147  virginica  
148  virginica  
149  virginica

What's happening behind the scenes is that Pandas knows how to use the diplay() function from IPython.

In [14]:
from IPython.display import display
In [15]:
display(df.head())
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa

The DataFrame.groupby() method

One of the most useful aspects of dataframes is the groupby() method, which returns an iterator that steps through the original dataframe by returning subsets (groups) which all have been selected based on a common value. An example will make this more clear.

Here we will step through our original dataframe grouping by species. The iterator from groupby() returns, on each iteration, a tuple of (group_value, group_data_frame). Let's look at this in action:

In [17]:
my_iterator = df.groupby('species')
for x in my_iterator:
    species, gdf = x
    print(f"species: Iris {species}")
    display(gdf.head())

species: Iris setosa
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa 
species: Iris versicolor
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
50 7.0 3.2 4.7 1.4 versicolor
51 6.4 3.2 4.5 1.5 versicolor
52 6.9 3.1 4.9 1.5 versicolor
53 5.5 2.3 4.0 1.3 versicolor
54 6.5 2.8 4.6 1.5 versicolor 
species: Iris virginica
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
100 6.3 3.3 6.0 2.5 virginica
101 5.8 2.7 5.1 1.9 virginica
102 7.1 3.0 5.9 2.1 virginica
103 6.3 2.9 5.6 1.8 virginica
104 6.5 3.0 5.8 2.2 virginica
In [18]:
for species, gdf in df.groupby('species'):
    print(f"species: Iris {species}")
    display(gdf.head())

species: Iris setosa
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa 
species: Iris versicolor
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
50 7.0 3.2 4.7 1.4 versicolor
51 6.4 3.2 4.5 1.5 versicolor
52 6.9 3.1 4.9 1.5 versicolor
53 5.5 2.3 4.0 1.3 versicolor
54 6.5 2.8 4.6 1.5 versicolor 
species: Iris virginica
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
100 6.3 3.3 6.0 2.5 virginica
101 5.8 2.7 5.1 1.9 virginica
102 7.1 3.0 5.9 2.1 virginica
103 6.3 2.9 5.6 1.8 virginica
104 6.5 3.0 5.8 2.2 virginica

Let's take a closer look at this iteration aspect:

In [19]:
my_iter = df.groupby('species')
print(type(my_iter))

<class 'pandas.core.groupby.generic.DataFrameGroupBy'>
In [20]:
my_iter = df.groupby('species')
for x in my_iter:
    # species = x[0]
    # gdf = x[1]
    species, gdf = x
    # (species, gdf) = x
    print(species, len(gdf))

setosa 50
versicolor 50
virginica 50
In [21]:
for species, gdf in df.groupby('species'):
    print(species, len(gdf))

setosa 50
versicolor 50
virginica 50
In [22]:
for species, gdf in df.groupby('species'):
    print(f"=============== {species} ============")
    display(gdf)

=============== setosa ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
5 5.4 3.9 1.7 0.4 setosa
6 4.6 3.4 1.4 0.3 setosa
7 5.0 3.4 1.5 0.2 setosa
8 4.4 2.9 1.4 0.2 setosa
9 4.9 3.1 1.5 0.1 setosa
10 5.4 3.7 1.5 0.2 setosa
11 4.8 3.4 1.6 0.2 setosa
12 4.8 3.0 1.4 0.1 setosa
13 4.3 3.0 1.1 0.1 setosa
14 5.8 4.0 1.2 0.2 setosa
15 5.7 4.4 1.5 0.4 setosa
16 5.4 3.9 1.3 0.4 setosa
17 5.1 3.5 1.4 0.3 setosa
18 5.7 3.8 1.7 0.3 setosa
19 5.1 3.8 1.5 0.3 setosa
20 5.4 3.4 1.7 0.2 setosa
21 5.1 3.7 1.5 0.4 setosa
22 4.6 3.6 1.0 0.2 setosa
23 5.1 3.3 1.7 0.5 setosa
24 4.8 3.4 1.9 0.2 setosa
25 5.0 3.0 1.6 0.2 setosa
26 5.0 3.4 1.6 0.4 setosa
27 5.2 3.5 1.5 0.2 setosa
28 5.2 3.4 1.4 0.2 setosa
29 4.7 3.2 1.6 0.2 setosa
30 4.8 3.1 1.6 0.2 setosa
31 5.4 3.4 1.5 0.4 setosa
32 5.2 4.1 1.5 0.1 setosa
33 5.5 4.2 1.4 0.2 setosa
34 4.9 3.1 1.5 0.2 setosa
35 5.0 3.2 1.2 0.2 setosa
36 5.5 3.5 1.3 0.2 setosa
37 4.9 3.6 1.4 0.1 setosa
38 4.4 3.0 1.3 0.2 setosa
39 5.1 3.4 1.5 0.2 setosa
40 5.0 3.5 1.3 0.3 setosa
41 4.5 2.3 1.3 0.3 setosa
42 4.4 3.2 1.3 0.2 setosa
43 5.0 3.5 1.6 0.6 setosa
44 5.1 3.8 1.9 0.4 setosa
45 4.8 3.0 1.4 0.3 setosa
46 5.1 3.8 1.6 0.2 setosa
47 4.6 3.2 1.4 0.2 setosa
48 5.3 3.7 1.5 0.2 setosa
49 5.0 3.3 1.4 0.2 setosa 
=============== versicolor ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
50 7.0 3.2 4.7 1.4 versicolor
51 6.4 3.2 4.5 1.5 versicolor
52 6.9 3.1 4.9 1.5 versicolor
53 5.5 2.3 4.0 1.3 versicolor
54 6.5 2.8 4.6 1.5 versicolor
55 5.7 2.8 4.5 1.3 versicolor
56 6.3 3.3 4.7 1.6 versicolor
57 4.9 2.4 3.3 1.0 versicolor
58 6.6 2.9 4.6 1.3 versicolor
59 5.2 2.7 3.9 1.4 versicolor
60 5.0 2.0 3.5 1.0 versicolor
61 5.9 3.0 4.2 1.5 versicolor
62 6.0 2.2 4.0 1.0 versicolor
63 6.1 2.9 4.7 1.4 versicolor
64 5.6 2.9 3.6 1.3 versicolor
65 6.7 3.1 4.4 1.4 versicolor
66 5.6 3.0 4.5 1.5 versicolor
67 5.8 2.7 4.1 1.0 versicolor
68 6.2 2.2 4.5 1.5 versicolor
69 5.6 2.5 3.9 1.1 versicolor
70 5.9 3.2 4.8 1.8 versicolor
71 6.1 2.8 4.0 1.3 versicolor
72 6.3 2.5 4.9 1.5 versicolor
73 6.1 2.8 4.7 1.2 versicolor
74 6.4 2.9 4.3 1.3 versicolor
75 6.6 3.0 4.4 1.4 versicolor
76 6.8 2.8 4.8 1.4 versicolor
77 6.7 3.0 5.0 1.7 versicolor
78 6.0 2.9 4.5 1.5 versicolor
79 5.7 2.6 3.5 1.0 versicolor
80 5.5 2.4 3.8 1.1 versicolor
81 5.5 2.4 3.7 1.0 versicolor
82 5.8 2.7 3.9 1.2 versicolor
83 6.0 2.7 5.1 1.6 versicolor
84 5.4 3.0 4.5 1.5 versicolor
85 6.0 3.4 4.5 1.6 versicolor
86 6.7 3.1 4.7 1.5 versicolor
87 6.3 2.3 4.4 1.3 versicolor
88 5.6 3.0 4.1 1.3 versicolor
89 5.5 2.5 4.0 1.3 versicolor
90 5.5 2.6 4.4 1.2 versicolor
91 6.1 3.0 4.6 1.4 versicolor
92 5.8 2.6 4.0 1.2 versicolor
93 5.0 2.3 3.3 1.0 versicolor
94 5.6 2.7 4.2 1.3 versicolor
95 5.7 3.0 4.2 1.2 versicolor
96 5.7 2.9 4.2 1.3 versicolor
97 6.2 2.9 4.3 1.3 versicolor
98 5.1 2.5 3.0 1.1 versicolor
99 5.7 2.8 4.1 1.3 versicolor 
=============== virginica ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm) species
100 6.3 3.3 6.0 2.5 virginica
101 5.8 2.7 5.1 1.9 virginica
102 7.1 3.0 5.9 2.1 virginica
103 6.3 2.9 5.6 1.8 virginica
104 6.5 3.0 5.8 2.2 virginica
105 7.6 3.0 6.6 2.1 virginica
106 4.9 2.5 4.5 1.7 virginica
107 7.3 2.9 6.3 1.8 virginica
108 6.7 2.5 5.8 1.8 virginica
109 7.2 3.6 6.1 2.5 virginica
110 6.5 3.2 5.1 2.0 virginica
111 6.4 2.7 5.3 1.9 virginica
112 6.8 3.0 5.5 2.1 virginica
113 5.7 2.5 5.0 2.0 virginica
114 5.8 2.8 5.1 2.4 virginica
115 6.4 3.2 5.3 2.3 virginica
116 6.5 3.0 5.5 1.8 virginica
117 7.7 3.8 6.7 2.2 virginica
118 7.7 2.6 6.9 2.3 virginica
119 6.0 2.2 5.0 1.5 virginica
120 6.9 3.2 5.7 2.3 virginica
121 5.6 2.8 4.9 2.0 virginica
122 7.7 2.8 6.7 2.0 virginica
123 6.3 2.7 4.9 1.8 virginica
124 6.7 3.3 5.7 2.1 virginica
125 7.2 3.2 6.0 1.8 virginica
126 6.2 2.8 4.8 1.8 virginica
127 6.1 3.0 4.9 1.8 virginica
128 6.4 2.8 5.6 2.1 virginica
129 7.2 3.0 5.8 1.6 virginica
130 7.4 2.8 6.1 1.9 virginica
131 7.9 3.8 6.4 2.0 virginica
132 6.4 2.8 5.6 2.2 virginica
133 6.3 2.8 5.1 1.5 virginica
134 6.1 2.6 5.6 1.4 virginica
135 7.7 3.0 6.1 2.3 virginica
136 6.3 3.4 5.6 2.4 virginica
137 6.4 3.1 5.5 1.8 virginica
138 6.0 3.0 4.8 1.8 virginica
139 6.9 3.1 5.4 2.1 virginica
140 6.7 3.1 5.6 2.4 virginica
141 6.9 3.1 5.1 2.3 virginica
142 5.8 2.7 5.1 1.9 virginica
143 6.8 3.2 5.9 2.3 virginica
144 6.7 3.3 5.7 2.5 virginica
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica
In [23]:
df.describe()
Out[23]:
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm)
count 150.000000 150.000000 150.000000 150.000000
mean 5.843333 3.057333 3.758000 1.199333
std 0.828066 0.435866 1.765298 0.762238
min 4.300000 2.000000 1.000000 0.100000
25% 5.100000 2.800000 1.600000 0.300000
50% 5.800000 3.000000 4.350000 1.300000
75% 6.400000 3.300000 5.100000 1.800000
max 7.900000 4.400000 6.900000 2.500000
In [24]:
for species, gdf in df.groupby('species'):
    print(f"=============== {species} ============")
    display(gdf.describe())

=============== setosa ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm)
count 50.00000 50.000000 50.000000 50.000000
mean 5.00600 3.428000 1.462000 0.246000
std 0.35249 0.379064 0.173664 0.105386
min 4.30000 2.300000 1.000000 0.100000
25% 4.80000 3.200000 1.400000 0.200000
50% 5.00000 3.400000 1.500000 0.200000
75% 5.20000 3.675000 1.575000 0.300000
max 5.80000 4.400000 1.900000 0.600000 
=============== versicolor ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm)
count 50.000000 50.000000 50.000000 50.000000
mean 5.936000 2.770000 4.260000 1.326000
std 0.516171 0.313798 0.469911 0.197753
min 4.900000 2.000000 3.000000 1.000000
25% 5.600000 2.525000 4.000000 1.200000
50% 5.900000 2.800000 4.350000 1.300000
75% 6.300000 3.000000 4.600000 1.500000
max 7.000000 3.400000 5.100000 1.800000 
=============== virginica ============
sepal length (cm) sepal width (cm) petal length (cm) petal width (cm)
count 50.00000 50.000000 50.000000 50.00000
mean 6.58800 2.974000 5.552000 2.02600
std 0.63588 0.322497 0.551895 0.27465
min 4.90000 2.200000 4.500000 1.40000
25% 6.22500 2.800000 5.100000 1.80000
50% 6.50000 3.000000 5.550000 2.00000
75% 6.90000 3.175000 5.875000 2.30000
max 7.90000 3.800000 6.900000 2.50000

More about Pandas DataFrames

Let's get started by making a sample dataframe with fake data:

In [25]:
sample_df = pd.DataFrame({'number':[1,2,3,6,2,3,2,2,1,2], 'color':['blue','blue','red','red','red','blue','blue','red','green','yellow']})
display(sample_df)
number color
0 1 blue
1 2 blue
2 3 red
3 6 red
4 2 red
5 3 blue
6 2 blue
7 2 red
8 1 green
9 2 yellow

Getting a Series from a DataFrame in Pandas

You can get a Series (a Pandas 1D array) from a dataframe column by indexing with the column name:

In [26]:
colors = sample_df['color']
display(colors)

0      blue
1      blue
2       red
3       red
4       red
5      blue
6      blue
7       red
8     green
9    yellow
Name: color, dtype: object

Above we got a Series from a DataFrame column with dictionary-like get item using square brackets and a string with the name of the column. In addition to this approach, Pandas also has an ergonomic feature where columns with names that are valid Python can be used with a dot (.) as if they were variables (also called "attributes") of the DataFrame instance.

In [27]:
# This does the same thing as above because "color" is a valid Python attribute name.

colors = sample_df.color
display(colors)

0      blue
1      blue
2       red
3       red
4       red
5      blue
6      blue
7       red
8     green
9    yellow
Name: color, dtype: object
In [28]:
type(colors)
Out[28]:
pandas.core.series.Series

A Series has many useful methods, such as .unique() and .mean()

In [29]:
colors.unique()
Out[29]:
array(['blue', 'red', 'green', 'yellow'], dtype=object)
In [30]:
sample_df['number'].mean()
Out[30]:
2.4
In [34]:
for color_name, color_df in sample_df.groupby('color'):
    print(color_name)
    display(color_df)

blue
number color
0 1 blue
1 2 blue
5 3 blue
6 2 blue 
green
number color
8 1 green 
red
number color
2 3 red
3 6 red
4 2 red
7 2 red 
yellow
number color
9 2 yellow

Pandas read_csv

CSV files are a very common and very good way to save data. Pandas has a good (and fast) reader for CSV files in the read_csv() function.

In [35]:
df = pd.read_csv('iris.csv')
In [36]:
df
Out[36]:
sepal_length sepal_width petal_length petal_width species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
... ... ... ... ... ...
145 6.7 3.0 5.2 2.3 virginica
146 6.3 2.5 5.0 1.9 virginica
147 6.5 3.0 5.2 2.0 virginica
148 6.2 3.4 5.4 2.3 virginica
149 5.9 3.0 5.1 1.8 virginica

150 rows × 5 columns

In [37]:
df.head()
Out[37]:
sepal_length sepal_width petal_length petal_width species
0 5.1 3.5 1.4 0.2 setosa
1 4.9 3.0 1.4 0.2 setosa
2 4.7 3.2 1.3 0.2 setosa
3 4.6 3.1 1.5 0.2 setosa
4 5.0 3.6 1.4 0.2 setosa
In [38]:
df['species'].unique()
Out[38]:
array(['setosa', 'versicolor', 'virginica'], dtype=object)

Conditions and selecting part of the data from a DataFrame.

Let's consider an equality condition. Let's check every row to test if the 'color' column is equal to 'blue':

In [39]:
sample_df
Out[39]:
number color
0 1 blue
1 2 blue
2 3 red
3 6 red
4 2 red
5 3 blue
6 2 blue
7 2 red
8 1 green
9 2 yellow
In [41]:
sample_df['color']
Out[41]:
0      blue
1      blue
2       red
3       red
4       red
5      blue
6      blue
7       red
8     green
9    yellow
Name: color, dtype: object
In [42]:
sample_df['color']=='blue'
Out[42]:
0     True
1     True
2    False
3    False
4    False
5     True
6     True
7    False
8    False
9    False
Name: color, dtype: bool

As usual, we can assign this result to a variable:

In [43]:
condition = sample_df['color']=='blue'

We can see the type of this result is another Series

In [44]:
type(condition)
Out[44]:
pandas.core.series.Series

One very useful thing in Pandas is to create a new DataFrame based on a condition from an old one. Let's make a new DataFrame from only the rows with a blue color:

In [45]:
condition = sample_df['color']=='blue'
blue_sample_df = sample_df[ condition ]
display(blue_sample_df)
number color
0 1 blue
1 2 blue
5 3 blue
6 2 blue

This could of course be written so:

In [46]:
blue_sample_df = sample_df[ sample_df['color']=='blue' ]
display(blue_sample_df)
number color
0 1 blue
1 2 blue
5 3 blue
6 2 blue

A key concept in Pandas is iterating over a dataframe, grouping by values in one (or more) columns

This allows doing a lot of powerful datascience work which requires nothing more than storing your data in a well-organized format. This of course has other advantages as well. Let's have a look at our groupby() example again:

In [1]:
import pandas as pd
df = pd.read_csv('iris.csv')
for species, gdf in df.groupby('species'):
    print(f"=============== {species} ============")
    display(gdf.describe())

=============== setosa ============
sepal_length sepal_width petal_length petal_width
count 50.00000 50.000000 50.000000 50.00000
mean 5.00600 3.418000 1.464000 0.24400
std 0.35249 0.381024 0.173511 0.10721
min 4.30000 2.300000 1.000000 0.10000
25% 4.80000 3.125000 1.400000 0.20000
50% 5.00000 3.400000 1.500000 0.20000
75% 5.20000 3.675000 1.575000 0.30000
max 5.80000 4.400000 1.900000 0.60000 
=============== versicolor ============
sepal_length sepal_width petal_length petal_width
count 50.000000 50.000000 50.000000 50.000000
mean 5.936000 2.770000 4.260000 1.326000
std 0.516171 0.313798 0.469911 0.197753
min 4.900000 2.000000 3.000000 1.000000
25% 5.600000 2.525000 4.000000 1.200000
50% 5.900000 2.800000 4.350000 1.300000
75% 6.300000 3.000000 4.600000 1.500000
max 7.000000 3.400000 5.100000 1.800000 
=============== virginica ============
sepal_length sepal_width petal_length petal_width
count 50.00000 50.000000 50.000000 50.00000
mean 6.58800 2.974000 5.552000 2.02600
std 0.63588 0.322497 0.551895 0.27465
min 4.90000 2.200000 4.500000 1.40000
25% 6.22500 2.800000 5.100000 1.80000
50% 6.50000 3.000000 5.550000 2.00000
75% 6.90000 3.175000 5.875000 2.30000
max 7.90000 3.800000 6.900000 2.50000

matplotlib + pandas + ❤️ = seaborn

Seaborn is "a Python data visualization library based on matplotlib. It provides a high-level interface for drawing attractive and informative statistical graphics." It makes heavy use of pandas to make your life easy.

In [2]:
import seaborn as sns
In [3]:
sns.stripplot(x="species", y="sepal_width", data=df);
In [4]:
sns.stripplot(x="species", y="sepal_width", data=pd.read_csv('iris.csv'));
In [5]:
sns.scatterplot(x="petal_width", y="sepal_width", data=pd.read_csv('iris.csv'), hue="species");

Let's take a minute to look at the seaborn gallery.

And while we are at it, we should not forget the matplotlib gallery.

</html>