evanyu800112 / dm_2018fall_lab2 Goto Github PK

This repository contains all the instructions and necessary code for Data Mining 2018 (Fall) lab session 2.

• Git clone:

    $ git clone https://github.com/EvanYu800112/dm_2018Fall_Lab2.git
  

• Download zip file: download link

Here is a list of the new required python libraries necessary for this lab session:
tensorflow, keras, gensim, scikit-learn

GoogleNews-vectors-negative300.bin.gz: download link
The data size is around 1.5GB, download it and put in ./GoogleNews/ directory. You do NOT need to decompress it.

Open a Jupyter notebook and run the following commands. If you have properly installed all the necessary libraries you should see no error.

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import itertools
import warnings
import sklearn
import gensim
import tensorflow
import keras

• part 1
  https://nbviewer.jupyter.org/github/EvanYu800112/dm_2018Fall_Lab2/blob/master/Lab02_part1.ipynb
• part 2
  https://nbviewer.jupyter.org/github/EvanYu800112/dm_2018Fall_Lab2/blob/master/Lab02_part2.ipynb

• part 1
  https://www.kaggle.com/evanyu800112/dm-2018fall-lab2-part1?scriptVersionId=7078126

• part 2
  https://www.kaggle.com/evanyu800112/dm-2018fall-lab2-p2?scriptVersionId=7081200 

• Deep Learning for NLP Python Notebooks in PyTorch and TensorFlow:
  https://github.com/omarsar/nlp_pytorch_tensorflow_notebooks

• Data Mining Lab Session 2 (Fall 2017):
  https://github.com/omarsar/data_mining_lab_fall_2