katreparitosh / data-analysis-of-indian-movies

A statistical analysis of Indian movies data set.

Stastical Analysis of Indian Movies

I analysed a dataset of Indian Movies primarily Hindi Movies.

Python Libraries Used :

• Pandas
• Numpy
• Matplotlib
• fivethirtyeight : A style which creates similar plots as that of FiveThirtyEight.

Questions tackled :

• Basic Exploration of Dataset.

  • Distribution of Ratings.
  • Gross collection in US and India.
  • Popularity of Genres.
  • Unique Stars and the number of roles they played.
  • Unique directors and the number of movies they directed.

• Factors affecting movie performance, based upon hypothesis.

  • Relationship between gross and genre.
  • Relationship between rating and genre.
  • Relationship between rating and gross.

• Trend of directors.

  • How many movies were directed by each director?
  • What genres do the directors stick to?
  • What are the popular genres for new/upcoming directors?

• Analysis of stars.

  • Who are the highest grossing stars comparing Indian and US Gross?
  • Who are the best rated stars?

Statistical Concepts used :

• Getting inferences from the outliers using IQR.
• IQR(Inter-quartile range)
• Skewness
• Median being used as a better average than mean.