Google Kaggle – Titanic Challenge Solution - Part 1
Summary
We are given a csv file with a total of 1309 data rows, each describes information gathered from every single Titanic passenger. Given below is the metadata describing our data source: Additionally, for 891 (i.e. up to 70%) of the passengers we get a “gender_submission” csv file telling us for a fact if they survived or died in the 1912 Titanic disaster. Given below is an awesome infographic I found which should give you a lot of insight on which “features” had the highest impact on survivability on board of Titanic. The second line is all that is required to load a csv file to a powerful data structure called Pandas DataFrame. Pandas DataFrames can be easily viewed and analysed using Pycharm (which is the highly-recommended IDE for Python data science) “Evaluate” and “View as DataFrame” feature: As you can see, we get heat-encoded visualisation of values in each column as well as detailed info on mean, standard deviation, min, max as well as the number of missing values, all in one place.
