Machine Learning - Data preprocessing

Machine Learning - Data preprocessing

·

3 min read

As part of my trying to complete Machine Learning A-Z Udemy course, this series of posts, starting with this one, will contain note I gather from it.

Dependent vs independent variables

  • Dependent – variable being tested and measured – predicted result
  • Independent – variable being changed or controlled – features

Used libraries(python):

  • numpy, a library containing mathematical tools
  • matplotlib.pyplot, plotting library
  • pandas – importing datasets
  • sklearn.preprocessing – library for processing data

Importing dataset with pandas:

import pandas as pd
pd.read_csv(FILE_NAME)

Missing data

Option 1:

  • remove rows with missing data
  • dangerous because we might be losing valuable information Option 2:
  • set missing values to mean of that feature

Library used:

sklearn.preprocessing.Imputer

Categorical data

Labels need to be converted into numbers - Euclidean distance can’t be calculated on labels Library:

sklearn.preprocessing.LabelEncoder

Problem with LabelEncoder: converting labels into numbers can lead to problems as numbers can be ordered. Labels not necessary Solution: Creating feature per label Library: sklearn.preprocessing.OneHotEncoder

Splitting data

For creating a model, data needs to be split into two sets, train and test. The train set is the one we use for creating a model, and the test is one we use to evaluate that mode's correctness. Library: sklearn.model_selection.train_test_split Usual ration: 70-80% for train data

Alt Text

Feature scaling

One feature, because of large values, can dominate the smaller number value feature. This is why all features should be scaled to the same scale. Option 1, standardization: Each value is reduced by the mean and divided by the standard deviation.

Alt Text

Option 2, normalization: Reduce each x by minimal x value. Ather that, divide by the difference between the maximum and minimum value of x.

Alt Text

Library:

sklearn.preprocessing.StandardScaler

For more, you can follow me on Twitter, LinkedIn, GitHub, or Instagram.