from blaze import Data, by, join, transform

bank = Data([[1, 'Alice',   100],
             [2, 'Bob',    -200],
             [3, 'Charlie', 300],
             [4, 'Dennis',  400],
             [5, 'Edith',  -500]], columns=['id', 'name', 'amount'])

bank.amount

bank.amount / 100

(bank.amount / 100).mean()

bank[['name', 'amount']].sort('amount')

bank[bank.amount < 0]

bank[bank.amount < 0].amount / 100

bank[bank.amount < 0].name

# What are the IDs of everyone with a positive amount?


# What is the name of the person with amount 400?


# What is the difference between the minimum and maximum amounts?


iris = Data('data/iris.csv')
iris

iris.dshape

iris.species.distinct()

iris.species.nunique()

iris.sepal_length.nunique()

transform(iris, sepal_ratio=iris.sepal_length / iris.sepal_width,
                petal_ratio=iris.petal_length / iris.petal_width)

by(iris.species, count=iris.species.count())

by(iris.species, count=iris.species.count(), 
                 longest_petal=iris.petal_length.max())

# What are the longest and shortest sepal_lengths per species?


# What is the difference of longest to shortest sepal length per species


import pandas as pd
df = pd.read_csv('data/iris.csv')
df.groupby(df.species).sepal_length.min()