Investigate_Dataset

Blog Version:

This Project is an Exploratory Data Analysis conducted on the TMDb dataset (a subset of IMDb dataset on Kaggle) provided via UdacityData Analyst NanoDegree [DAND] Resources.
It contains 2 CSV files with the cleaned data used for the data analysis. Data cleaning steps performed are mentioned in the .pynb files
Investigate_a_Dataset and Investigate_a_Dataset_TMDb are the initial passes of EDA used to formulate the Questions to be answered by detailed investigation.
Investigate_a_Dataset_TMDb_NirupamaPV.pynb is the final submission for Udacity’s DAND third assignment.
Investigate_a_Dataset_TMDb_Directors_NirupamaPV.pynb is my own EDA to see the dataset with an angle of Directorial Influence over movies, ratings and revenues.
.pynb files contain Markdowns (Git flavor) to explain steps and rationale of the analysis performed

Research Question 1 : How are runtimes, popularity and revenues trending over time?
Research Question 2 : What variables are associated with the revenues of movies spanning the years? If so, how?

Research Question 1 : Over the years, who are the popular directors?
Research Question 2 : What are typical runtimes for directors? Is there a duration preferred by directors?
Research Question 3 : What are typical revenues for directors? Who are the most successful directors?
Research Question 4 : Is there a relation between popularity and revenue for directors?