"""
Logistic Regression

Logistic regression (logit model) is a generalized linear model used for binomial regression. Logistic regression applies maximum likelihood estimation after transforming the dependent into a logit variable. 

"""


from smile.data import AttributeDataset,NominalAttribute
from smile.data.parser import DelimitedTextParser,IOUtils
from java.io import File
from jhplot import *
from smile.classification import LogisticRegression 
from jarray import zeros,array
from java.awt import Color
import java


# this function extract data[][] and label[] array from datasets
def getJavaArrays(dataset):
    rows=dataset.size()
    lst = [0.0]*rows
    twoDimArr = array([lst,[]], java.lang.Class.forName('[D'))
    data = dataset.toArray(twoDimArr)
    label = dataset.toArray(zeros(rows, "i"))
    return data,label

http="http://datamelt.org/examples/data/classification/toy/"
print "Reading data from",http
datasource="toy-train.txt"  
datasetName="Toy"
print Web.get(http+datasource)
parser =DelimitedTextParser()
parser.setDelimiter("[\t ]+")
parser.setResponseIndex(NominalAttribute("class"), 0)
dataset=parser.parse(datasetName,File(datasource))
print dataset
print "Classification.."

"""
lambda (> 0) gives a "regularized" estimate of linear weights 
"""
lamb=0.2
data,label=getJavaArrays(dataset)
lr=LogisticRegression(data, label, lamb)

# now we will use another sample for prediction
print "Training finished. Get a new sample for predictions.."
datasource="toy-test.txt" #  (20k events) 
datasetName="Testing"
print Web.get(http+datasource)
dataset=parser.parse(datasetName,File(datasource))
data,label=getJavaArrays(dataset)

#print label
#print type(data)
prediction=lr.predict(data)
rows=dataset.size()


c1 = HPlot("Canvas",800,450,2,1)
c1.visible()
c1.setAutoRange()
c1.setGTitle("Logistic Regression")

def applyStyle(p1,color,t): 
      p1.setSymbol(t); p1.setColor(color); p1.setSymbolSize(1); 
 
p1=P1D("Input true"); applyStyle(p1,Color.blue, 11);
p2=P1D("Input false"); applyStyle(p2,Color.red, 4); 
p1p=P1D("Predicted true"); applyStyle(p1p,Color.blue, 11);
p2p=P1D("Predicted false"); applyStyle(p2p,Color.red, 4);   

e=0.0
for i in range(rows):
    minput=data[i].tolist()
    expected=label[i]
    predicted=prediction[i] 
    if (expected>0): p1.add(minput[0],minput[1]) 
    else:            p2.add(minput[0],minput[1])
    if (predicted>0): p1p.add(minput[0],minput[1])
    else:             p2p.add(minput[0],minput[1])
    if (i%100==0): print "Input=",minput, " outcome=",expected," prediction=",predicted
    if (expected != predicted): e=e+1.0
e=e/rows
print "Error rate=",e

c1.cd(1,1)
c1.draw([p1,p2])
c1.cd(2,1)
c1.setAutoRange()
c1.draw([p1p,p2p])