hurshd0 / kaggle-news-analysis

Kaggle News NLP Analysis

Dataset

• Snapcrack All the News

Deliverable

• Powerpoint Analysis

Objectives

1. What are the most important events that occurred during the timeframe these articles were captured? How do these change over time in the dataset?
2. Lockheed Martin is part of an expensive and ever-changing Aerospace and Defence industry. In order to better understand the playing field, perform an analysis that would allow a stakeholder to make an informed startegic business decision regarding an action the company should take with respect to the Aerospace and Defense landscape.

Usage

Pre-requisites

• Python 3.8

1. Install Pipenv for managing python based virtual environment, pip install pipenv

NOTE: If you have conda installed with different Python base environment follow below steps

• Step 1. Create Python 3.8 in conda virtual environment - conda create -n py38 python=3.8 -y
• Step 2. Install pipenv inside conda - conda install -c conda-forge pipenv
• Step 3. Find python path where python 3.8 is installed - which python
• Step 4. Install dependencies, pipenv install --python <python path> for e.g. mine is /home/ubuntu/miniconda3/envs/py38/bin/python

Now go to 3. and activate virtual environment.

2. Create virtual environment pipenv install
3. Activate virtual environment pipenv shell
4. Open Jupyter Notebook jupyter notebook