import pandas as pd
import numpy as np

# 'characters' is equivalent to string
firstName = 'jeff'
print type(firstName), firstName

# 'numeric' is equivalent to float
heightCM = 188.2
print type(heightCM), heightCM

# integer is equivalent to integer
numberSons = 1
print type(numberSons), numberSons

# 'logical' is equivalent to Boolean
teachingCoursera = True
print type(teachingCoursera), teachingCoursera

# 'vectors' is equivalent to numpy array or Python list (I will use array everywhere for consistency)
heights = np.array([188.2, 181.3, 193.4])
print heights

firstNames = np.array(['jeff', 'roger', 'andrew', 'brian'])
print firstNames

# 'list' is equivalent to dictionary in Python
vector1 = np.array([188.2, 181.3, 193.4])
vector2 = np.array(['jeff', 'roger', 'andrew', 'brian'])
myList = dict(heights = vector1, firstNames = vector2)
print myList

print myList['heights']
print myList['firstNames']

# 'matrices' is equivalent to two-dimensional numpy array
myMatrix = np.array([[1, 2], [3, 4]])
print myMatrix

# data frame is equivalent to Pandas DataFrame
# this example doesn't work because the input array lengths are not the same
vector1 = np.array([188.2, 181.3, 193.4])
vector2 = np.array(['jeff', 'roger', 'andrew', 'brian'])

# ValueError: arrays must all be same length
# 
myDataFrame = pd.DataFrame(dict(heights = vector1, firstNames = vector2))

# data frame -- fixed
vector1 = np.array([188.2, 181.3, 193.4, 192.3])
vector2 = np.array(['jeff', 'roger', 'andrew', 'brian'])

myDataFrame = pd.DataFrame(dict(heights = vector1, firstNames = vector2))
myDataFrame

# factors is equivalent to pandas Categorical
smoker = np.array(['yes', 'no', 'yes', 'yes'])
smokerFactor = pd.Categorical.from_array(smoker)
smokerFactor

# R's NA missing values is equivalent to NaN
vector1 = np.array([188.2, 181.3, 193.4, NaN])
print vector1
print isnan(vector1)

# subsetting
vector1 = np.array([188.2, 181.3, 193.4, 192.3])
vector2 = np.array(['jeff', 'roger', 'andrew', 'brian'])

myDataFrame = pd.DataFrame(dict(heights = vector1, firstNames = vector2))

print '------------------'
print vector1[0]
print '------------------'
print vector1[[0, 1, 3]]
print '------------------'
print myDataFrame.ix[0, 0:2] # appears transposed as compared to R
print '------------------'
print myDataFrame['firstNames'] # there's no 'Levels' as in R
print '------------------'
print myDataFrame[myDataFrame['firstNames'] == 'jeff']
print '------------------'
print myDataFrame[myDataFrame['heights'] < 190]