Python for Text Classification with Machine Learning in Python 3.6.

Start your environment by picking either pipenv (recommended) or virtualenv. Simple guides are below.

1. Initialize pipenv (setup guide):

cd path/to/your/dev/folder
mkdir text-classify
cd text-classify
pipenv install --three

After installation of pipenv works, just activate it (same on all systems):

pipenv shell

2. Project requirements

pip install numpy scipy scikit-learn jupyter

1. Initialize virtualenv

cd path/to/your/dev/folder
mkdir text-classify
cd text-classify
virtualenv --python3 .

After installation of pipenv works, just activate it:

Mac / Linux

source bin/activate

Windows

.\Scripts\activate

2. Project requirements

pip install numpy scipy scikit-learn jupyter

1 - Introduction no code

2 - Initialize Virtual Environment with Pipenv

3 - Sublime Text & Jupyter Notebooks no code

4 - Bag of Words

5 - One Hot Array

6 - Bag of Words Function

7 - One Hot Array Function

8 - One Hot Array Back to Text

9 - Bag of Words with External Data

10 - One Hot Array with External Data

11 - Training Data and Labels as Numpy Arrays

12 - Train and Predict with Sklearn SVM

13 - Text Prediction Recap

14 - Reusable Sklearn Classifier

15 - Missing Bow

16 - Pickles no code

17 - Good Data In, Good Data Out no code

18 - Dataset Resources no code Blog Post

19 Grab and Parse Dataset

20 - Prepare Training Module for Spam + Not Spam

21 - Train Spam Classifier with SVC

22 - Clean and Predict

23 - Scoring Classifier Accuracy

24 - One Hot Encoding Classification Recap

25 - Preprocessing with a Keras Tokenizer

26 - Pad Sequences

27 - Convert Our Text Data into Sequences

28 - Labels and LabelEncoder

29 - Reusable Text-Label Utility

30 - Split Training and Validation Data

31 - Tokenized Text Classifier

32 - Cross Validation

33 - Sensitivity vs Specificity