Skip to content

Commit 03937e6

Browse files
micahkwokmicahkwok
authored
Merge pull request #18 from UBC-MDS/imputer
merge Imputer method specification and changes in CONTRIBUTING.rst
2 parents 2975c27 + 43bbffa commit 03937e6

File tree

6 files changed

+596
-65
lines changed

6 files changed

+596
-65
lines changed

‎CONTRIBUTING.rst‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,6 +7,17 @@ Contributing
77
Contributions are welcome, and they are greatly appreciated! Every little bit
88
helps, and credit will always be given.
99

10+
Contributor Agreement
11+
----------------------
12+
13+
By contributing,
14+
you agree that we may redistribute your work under our license.
15+
In exchange,
16+
we will address your issues and/or assess your change proposal as promptly as
17+
we can, and help you become a member of our community.
18+
Everyone involved agrees to abide by our
19+
code of conduct.
20+
1021
You can contribute in many ways:
1122

1223
Types of Contributions

‎docs/source/eda_utils_py.rst‎

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
eda\_utils\_py package
2+
======================
3+
4+
Submodules
5+
----------
6+
7+
eda\_utils\_py.eda\_utils\_py module
8+
------------------------------------
9+
10+
.. automodule:: eda_utils_py.eda_utils_py
11+
:members:
12+
:undoc-members:
13+
:show-inheritance:
14+
15+
Module contents
16+
---------------
17+
18+
.. automodule:: eda_utils_py
19+
:members:
20+
:undoc-members:
21+
:show-inheritance:

‎docs/source/modules.rst‎

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,7 @@
1+
eda_utils_py
2+
============
3+
4+
.. toctree::
5+
:maxdepth: 4
6+
7+
eda_utils_py

‎eda_utils_py/eda_utils_py.py‎

Lines changed: 124 additions & 64 deletions
Original file line numberDiff line numberDiff line change
@@ -1,88 +1,148 @@
1-
def cor_map(dataframe, num_col):
1+
def imputer(dataframe, strategy="mean", fill_value=None):
22
"""
3-
A function to implement a correlation heatmap including coefficients based on given numeric columns of a data frame.
4-
5-
Args:
6-
dataframe (pandas.DataFrame): The data frame to be used for EDA.
7-
num_col (list): A list of string of column names with numeric data from the data frame.
8-
9-
Returns:
10-
(altair): A correlation heatmap plot with correlation coefficient labels based on the numeric columns specified by user.
3+
A function to implement imputation functionality for completing missing values.
4+
5+
Parameters
6+
----------
7+
dataframe : pandas.core.frame.DataFrame
8+
a dataframe that might contain missing data
9+
strategy : string, default="mean"
10+
The imputation strategy.
11+
- If “mean”, then replace missing values using the mean along each column. Can only be used with numeric data.
12+
- If “median”, then replace missing values using the median along each column. Can only be used with numeric data.
13+
- If “most_frequent”, then replace missing using the most frequent value along each column. Can be used with strings or numeric data. If there is more than one such value, only the smallest is returned.
14+
- If “constant”, then replace missing values with fill_value. Can be used with strings or numeric data.
15+
fill_value : string or numerical value, default=None
16+
When strategy == “constant”, fill_value is used to replace all occurrences of missing_values. If left to the default, fill_value will be 0 when imputing numerical data and “missing_value” for strings or object data types.
17+
18+
Returns
19+
-------
20+
pandas.core.frame.DataFrame
21+
a dataframe that contains no missing data
22+
23+
Examples
24+
---------
25+
>>> import pandas as pd
26+
>>> from eda_utils_py import cor_map
27+
28+
>>> data = pd.DataFrame({
29+
>>> 'SepalLengthCm':[5.1, 4.9, 4.7],
30+
>>> 'SepalWidthCm':[1.4, 1.4, 1.3],
31+
>>> 'PetalWidthCm':[0.2, None, 0.2]
32+
>>> })
33+
34+
>>> imputer(data, numerical_columns)
35+
SepalLengthCm SepalWidthCm PetalWidthCm
36+
0 5.1 1.4 0.2
37+
1 4.9 1.4 0.2
38+
2 4.7 1.3 0.2
39+
"""
40+
pass
1141

12-
Examples:
13-
import pandas as pd
14-
from eda_utils_py import cor_map
1542

16-
data = pd.DataFrame({
17-
'SepalLengthCm':[5.1, 4.9, 4.7],
18-
'SepalWidthCm':[1.4, 1.4, 1.3],
19-
'PetalWidthCm:[0.2, 0.2, 0.2],
20-
'Species':['Iris-setosa','Iris-virginica']
21-
})
43+
def cor_map(dataframe, num_col):
44+
"""
45+
A function to implement a correlation heatmap including coefficients based on given numeric columns of a data frame.
2246
23-
numerical_columns = ['SepalLengthCm','SepalWidthCm','PetalWidthCm']
24-
25-
cor_map(data, numerical_columns)
47+
Parameters
48+
----------
49+
dataframe : pandas.core.frame.DataFrame
50+
The data frame to be used for EDA.
51+
num_col : list
52+
A list of string of column names with numeric data from the data frame.
53+
54+
Returns
55+
-------
56+
altair.vegalite.v4.api.Chart
57+
A correlation heatmap plot with correlation coefficient labels based on the numeric columns specified by user.
58+
59+
Examples
60+
---------
61+
>>> import pandas as pd
62+
>>> from eda_utils_py import cor_map
63+
64+
>>> data = pd.DataFrame({
65+
>>> 'SepalLengthCm':[5.1, 4.9, 4.7],
66+
>>> 'SepalWidthCm':[1.4, 1.4, 1.3],
67+
>>> 'PetalWidthCm':[0.2, 0.2, 0.2],
68+
>>> 'Species':['Iris-setosa','Iris-virginica', 'Iris-germanica']
69+
>>> })
70+
71+
>>> numerical_columns = ['SepalLengthCm','SepalWidthCm','PetalWidthCm']
72+
>>> cor_map(data, numerical_columns)
2673
2774
"""
75+
pass
2876

2977

30-
def outlier_identifier(dataframe, columns=None, method="somefunction"):
78+
def outlier_identifier(dataframe, columns=None, method="trim"):
3179
"""
3280
A function that identify and deal with outliers based on the method the user choose
3381
34-
Key arguments:
35-
dataframe [pandas.DataFrame]:
36-
The target dataframe where the function is performed.
37-
columns [list] : None
38-
The target columns where the function needed to be performed. Defualt is None, the function will check all columns
39-
method [string] : "somefunction"
40-
The method of dealing with outliers.
82+
Parameters
83+
----------
84+
dataframe : pandas.core.frame.DataFrame
85+
The target dataframe where the function is performed.
86+
columns : list, default=None
87+
The target columns where the function needed to be performed. Defualt is None, the function will check all columns
88+
method : string
89+
The method of dealing with outliers.
90+
- if "trim" : we completely remove data points that are outliers.
91+
- if "median" : we replace outliers with median values
4192
42-
Returns:
43-
dataframe :
44-
The dataframe which the outlier has already process by the chosen method
93+
Returns
94+
-------
95+
pandas.core.frame.DataFrame
96+
a dataframe which the outlier has already process by the chosen method
4597
46-
Examples:
47-
data = pd.DataFrame({
48-
'SepalLengthCm':[5.1, 4.9, 4.7],
49-
'SepalWidthCm':[1.4, 1.4, 9999999.99],
50-
'PetalWidthCm:[0.2, 0.2, 0.2],
51-
'Species':['Iris-setosa','Iris-virginica']
52-
})
98+
Examples
99+
--------
100+
>>> import pandas as pd
101+
>>> from eda_utils_py import cor_map
102+
103+
>>> data = pd.DataFrame({
104+
>>> 'SepalLengthCm':[5.1, 4.9, 4.7],
105+
>>> 'SepalWidthCm':[1.4, 1.4, 9999999.99],
106+
>>> 'PetalWidthCm:[0.2, 0.2, 0.2],
107+
>>> 'Species':['Iris-setosa', 'Iris-virginica', 'Iris-germanica']
108+
>>> })
53109
54-
outlier_identifier(data)
110+
>>> outlier_identifier(data)
55111
56112
"""
113+
pass
57114

58115

59116
def scale(dataframe, columns=None):
60117
"""
61118
A function to scale features by removing the mean and scaling to unit variance
62-
.
63-
64-
Args:
65-
dataframe (pandas.DataFrame): The data frame to be used for EDA.
66-
columns (list): A list of string of column names with numeric data from the data frame that we wish to scale.
67-
68-
Returns:
69-
dataframe :
70-
The scaled dataframe for numerical features
71-
72-
Examples:
73-
import pandas as pd
74-
from eda_utils_py import scale
75-
76-
data = pd.DataFrame({
77-
'SepalLengthCm':[5.1, 4.9, 4.7],
78-
'SepalWidthCm':[1.4, 1.4, 1.3],
79-
'PetalWidthCm:[0.2, 0.2, 0.2],
80-
'Species':['Iris-setosa','Iris-virginica']
81-
})
82-
83-
numerical_columns = ['SepalLengthCm','SepalWidthCm','PetalWidthCm']
84-
85-
scale(data, numerical_columns)
86119
120+
Parameters
121+
----------
122+
dataframe : pandas.DataFrame
123+
The data frame to be used for EDA.
124+
columns : list, default=None
125+
A list of string of column names with numeric data from the data frame that we wish to scale.
126+
127+
Returns
128+
-------
129+
dataframe : pandas.core.frame.DataFrame
130+
The scaled dataframe for numerical features
131+
132+
Examples
133+
--------
134+
>>> import pandas as pd
135+
>>> from eda_utils_py import scale
136+
137+
>>> data = pd.DataFrame({
138+
>>> 'SepalLengthCm':[5.1, 4.9, 4.7],
139+
>>> 'SepalWidthCm':[1.4, 1.4, 1.3],
140+
>>> 'PetalWidthCm:[0.2, 0.2, 0.2],
141+
>>> 'Species':['Iris-setosa','Iris-virginica', 'Iris-germanica']
142+
>>> })
143+
144+
>>> numerical_columns = ['SepalLengthCm','SepalWidthCm','PetalWidthCm']
145+
146+
>>> scale(data, numerical_columns)
87147
"""
88148
pass

0 commit comments

Comments
 (0)