Created
July 22, 2014 22:54
-
-
Save leonaburime/c9fc192b5c215367236e to your computer and use it in GitHub Desktop.
File used to read in data -possibly into dataframes - for various sample python programs.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import urllib2, pandas as pd | |
d = { | |
'mushroom' :{ | |
'features': [ | |
'class','cap-shape', 'cap-surface', 'cap-color', | |
'bruises?','odor','gill-attachment', | |
'gill-spacing', 'gill-size', 'gill-color', | |
'stalk-shape', 'stalk-root', 'stalk-surface-above-ring', | |
'stalk-surface-below-ring', 'stalk-color-above-ring', | |
'stalk-color-below-ring','veil-type', 'veil-color', | |
'ring-number', 'ring-type', 'spore-print-color', | |
'population', 'habitat' | |
], | |
'file': 'Data/agaricus-lepiota.data', | |
'outcome_options' : {'good':'e', 'bad':'p', 'default': 'p'}, | |
'outcome_name' : 'class', | |
#'url': urllib2.urlopen('https://archive.ics.uci.edu/ml/machine-learning-databases/mushroom/agaricus-lepiota.data'), | |
}, | |
'play':{ | |
'features':['outlook','temperature','humidity','wind','play'], | |
'features_attributes':{ | |
'outlook':['sunny','overcast', 'rain'], | |
'temperature':['hot', 'mild', 'cool'], | |
'humidity':['high', 'normal', 'low'], | |
'wind':['weak','strong'], | |
'play':['yes','no'] | |
}, | |
'file':'Data/play.txt', | |
'outcome_name':'play', | |
'outcome_options':{'yes','no'} | |
} | |
} | |
def get(name, d=d): | |
return d[name] | |
def createDataFrame( column_names, datafile, testSize=0): | |
data = [] | |
#Now we are going to open up the mushroom file and read it line by line | |
for line in open(datafile).readlines(): | |
if '?' in line: continue #Lets filter out the values which are incomplete | |
#Lets strip whitespaces and split the values into lists to append them to our data list | |
data.append( line.strip().split(',') ) | |
#print line.strip().split(',') #Uncomment line below to see what type of data you are getting | |
#Lets create the dataframe w/ 'features' as column attributes and data as rows | |
test,train = None, None | |
train = pd.DataFrame(data[testSize:], columns=column_names) #Training set | |
if testSize > 0: | |
test = pd.DataFrame(data[:testSize], columns=column_names) #Test set | |
return train, test | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment