import pandas import pandasql def aggregate_query(filename): aadhaar_data = pandas.read_csv(filename) aadhaar_data.rename(columns = lambda x: x.replace(' ', '_').lower(), inplace=True) q = """ SELECT gender, district, sum(aadhaar_generated) FROM aadhaar_data WHERE age > 50 GROUP BY gender, district; """ aadhaar_solution = pandasql.sqldf(q.lower(), locals()) return aadhaar_solution
Files, Databases, APIs
Application Programming Interface
https://www.last.fm/api
import json import requests def imputation(filename): baseball = pandas.read_csv('../data/Master.csv') baseball['weight'] = baseball['weight'].fillna(numpy.mean(baseball['weight'])) print numpy.sum(baseball['weight']), numpy.mean(baseball['weight'])