Udacity MLND Capstone

Capstone project for Udacity's Machine Learning Nanodegree

Problem Statement

This is a classification problem. Inputs will be the building details and the output will be the prediction of the extent of damage that has been done to a building after an earthquake. The damage to a building is categorized in five grades. Each grade depicts the extent of damage done to a building post an earthquake.

Datasets

In this dataset consist of the before and after details of nearly one million buildings after an earthquake provided by the hackerearth. This dataset is free to download.

RangeIndex: 631761 entries, 0 to 631760 Data columns (total 14 columns): area_assesed 631761 non-null object building_id 631761 non-null object damage_grade 631761 non-null object district_id 631761 non-null int64 has_geotechnical_risk 631761 non-null float64 has_geotechnical_risk_fault_crack 631761 non-null int64 has_geotechnical_risk_flood 631761 non-null int64 has_geotechnical_risk_land_settlement 631761 non-null int64 has_geotechnical_risk_landslide 631761 non-null int64 has_geotechnical_risk_liquefaction 631761 non-null int64 has_geotechnical_risk_other 631761 non-null int64 has_geotechnical_risk_rock_fall 631761 non-null int64 has_repair_started 598344 non-null float64 vdcmun_id 631761 non-null int64 dtypes: float64(2), int64(9), object(3) memory usage: 67.5+ MB

Requirements

• Python 3.5
• Jupyter Notebook / Ipython
• Anaconda (preferred, not necessary)

Python libraries

• matplotlib
• sklearn
• numpy
• pandas
• seaborn
• tqdm
• matplotlib

Run

• Open Jupyter Notebook mlnd_capstone_project.ipynb in the root folder.