Preprocessing

Data analysis - EDA

Dataset preprocessing examples

from mlearner.preprocessing import DataAnalyst

import numpy as np
import pandas as pd

from mlearner.preprocessing import DataAnalyst

%matplotlib inline

Load data in base_preprocess class

filename = "mlearner/data/data/breast-cancer-wisconsin-data.txt"
dataset = DataAnalyst.load_data(filename, sep=",")

dataset.data.head(5)
Sample code number Clump Thickness Uniformity of Cell Size Uniformity of Cell Shape Marginal Adhesion Single Epithelial Cell Size Bare Nuclei Bland Chromatin Normal Nucleoli Mitoses Class
0 1000025 5 1 1 1 2 1 3 1 1 2
1 1002945 5 4 4 5 7 10 3 2 1 2
2 1015425 3 1 1 1 2 2 3 1 1 2
3 1016277 6 8 8 1 3 4 3 7 1 2
4 1017023 4 1 1 3 2 1 3 1 1 2 
dataset.dtypes()

Sample code number              int64
Clump Thickness                 int64
Uniformity of Cell Size         int64
Uniformity of Cell Shape        int64
Marginal Adhesion               int64
Single Epithelial Cell Size     int64
Bare Nuclei                    object
Bland Chromatin                 int64
Normal Nucleoli                 int64
Mitoses                         int64
Class                           int64
dtype: object

target = ["Class"]

Method: boxplot

dataset.boxplot(features=["Bland Chromatin", "Clump Thickness"], 
                target=target)

png

Method: dispersion_categoria

dataset.dispersion_categoria(target=target)

png

Method: sns_jointplot

dataset.sns_jointplot(feature1=["Bland Chromatin"], feature2=["Clump Thickness"], target=target, 
                      categoria1 = [2])

png

Method: sns_pairplot

dataset.sns_pairplot(features= ["Bland Chromatin", "Clump Thickness"], target=target)

png

Method: distribution_targets

dataset.distribution_targets(target=target)

png

Method: corr_matrix

dataset.corr_matrix()

png

Method: not_type_object

API