Logistic Regression in IronPython QuickStart Sample
Illustrates how to use the LogisticRegressionModel class to create logistic regression models in IronPython.
View this sample in: C# Visual Basic F#
```Python
import numerics
from System import Char, Array
from Extreme.Statistics import *
from Extreme.Mathematics import *
from Extreme.Mathematics.LinearAlgebra.IO import *
# Illustrates building logistic regression models using
# the LogisticRegressionModel class in the
# Extreme.Statistics namespace of the Extreme
# Optimization Numerical Libraries for .NET.
# Logistic regression can be performed using
# the LogisticRegressionModel class.
#
# This QuickStart sample uses data from a study of factors
# that determine low birth weight at Baystate Medical Center.
# from Belsley, Kuh and Welsch. The fields are as follows:
# AGE: Mother's age.
# LWT: Mother's weight.
# RACE: 1=white, 2=black, 3=other.
# FVT: Number of physician visits during the 1st trimester.
# LOW: Low birth weight indicator.
# First, read the data from a file into an ADO.NET DataTable.
# For the sake of clarity, we put this code in its own method.
import clr
clr.AddReference("System.Data")
from System.Data import *
from System.IO import *
# <summary>
# Reads the data from a text file into a <see cref="DataTable"/>.
# </summary>
# <returns>A <see cref="DataTable"/></returns>
def ReadData():
data = DataTable("LowBirthWeight")
# data.Columns.Add("Key", typeof(string))
whitespace = Array[Char]([ ' ', '\t' ])
sr = StreamReader(r"..\Data\lowbwt.txt")
# Read the header and extract the field names.
line = sr.ReadLine()
pos = 0
while True:
while Char.IsWhiteSpace(line[pos]):
pos = pos + 1
pos2 = line.IndexOfAny(whitespace, pos)
if pos2 < 0:
data.Columns.Add(line.Substring(pos), float)
break
else:
data.Columns.Add(line.Substring(pos, pos2 - pos), float)
pos = pos2
if pos < 0:
break
# Now read the data and add them to the table.
# Assumes all columns except the first are numerical.
rowData = Array.CreateInstance(object, data.Columns.Count)
line = sr.ReadLine()
while line != None and line.Length > 0:
column = 0
pos = 0
while True:
while Char.IsWhiteSpace(line[pos]):
pos = pos + 1
pos2 = line.IndexOfAny(whitespace, pos)
if pos2 < 0:
field = line.Substring(pos)
else:
field = line.Substring(pos, pos2 - pos)
if column == 0:
rowData[column] = field
else:
rowData[column] = float.Parse(field)
column = column + 1
pos = pos2
if pos < 0 or column >= data.Columns.Count:
break
data.Rows.Add(rowData)
line = sr.ReadLine()
return data
dataTable = ReadData()
data = VariableCollection(dataTable)
# We need indicator variables for the race. We use the
# CreateIndicatorVariable method:
race = data["RACE"]
race2 = race.CreateIndicatorVariable(2.0)
data.Add(race2)
race3 = race.CreateIndicatorVariable(3.0)
data.Add(race3)
# Now create the regression model. Parameters are the name
# of the dependent variable, a string array containing
# the names of the independent variables, and the VariableCollection
# containing all variables.
model = LogisticRegressionModel(data, "LOW", Array[str] ([ "AGE", "LWT", "RACE(2)", "RACE(3)", "FTV" ]))
# The Compute method performs the actual regression analysis.
model.Compute()
# The Parameters collection contains information about the regression
# parameters.
print "Variable Value Std.Error t-stat p-Value"
for parameter in model.Parameters:
# Parameter objects have the following properties:
print "{0:20}{1:10.5f}{2:10.5f}{3:8.2f} {4:7.4f}".format( # Name, usually the name of the variable:
parameter.Name, # Estimated value of the parameter:
parameter.Value, # Standard error:
parameter.StandardError, # The value of the t statistic for the hypothesis that the parameter
# is zero.
parameter.Statistic, # Probability corresponding to the t statistic.
parameter.PValue)
# The log-likelihood of the computed solution is also available:
print "Log-likelihood: {0:.4f}".format( model.GetLogLikelihood())
# We can test the significance by looking at the results
# of a log-likelihood test, which compares the model to
# a constant-only model:
lrt = model.GetLikelihoodRatioTest()
print "Likelihood-ratio test: chi-squared={0:.4f}, p={1:.4f}".format(lrt.Statistic, lrt.PValue)
print
# We can compute a model with fewer parameters:
model2 = LogisticRegressionModel(data, "LOW", Array[str] ([ "LWT", "RACE(2)", "RACE(3)" ]))
model2.Compute()
# Print the results...
print "Variable Value Std.Error t-stat p-Value"
for parameter in model2.Parameters:
print "{0:20}{1:10.5f}{2:10.5f}{3:8.2f} {4:7.4f}".format( \
parameter.Name, parameter.Value, parameter.StandardError, parameter.Statistic, parameter.PValue)
# ...including the log-likelihood:
print "Log-likelihood: {0:.4f}".format(model.GetLogLikelihood())
# We can now compare the original model to this one, once again
# using the likelihood ratio test:
lrt = model.GetLikelihoodRatioTest(model2)
print "Likelihood-ratio test: chi-squared={0:.4f}, p={1:.4f}".format(lrt.Statistic, lrt.PValue)
print
#
# Multinomial (polytopous) logistic regression
#
# The LogisticRegressionModel class can also be used
# for logistic regression with more than 2 responses.
# The following example is from "Applied Linear Statistical
# Models."
# Load the data into a matrix
from System.Globalization import NumberStyles
reader = FixedWidthMatrixReader( \
File.OpenText(r"..\Data\mlogit.txt"), 0, \
Array[int]([5, 10, 15, 20, 25, 32, 37, 42, 47 ]), \
NumberStyles.Integer, None)
m = reader.ReadMatrix()
# Next, convert the columns to variables.
# For multinomial regression, the response variable must be
# a CategoricalVariable:
duration = NumericalVariable("duration", m.GetColumn(1)).ToCategoricalVariable()
nutritio = NumericalVariable("nutritio", m.GetColumn(5))
agecat1 = NumericalVariable("agecat1", m.GetColumn(6))
agecat3 = NumericalVariable("agecat3", m.GetColumn(7))
alcohol = NumericalVariable("alcohol", m.GetColumn(8))
smoking = NumericalVariable("smoking", m.GetColumn(9))
# The constructor takes an extra argument of type
# LogisticRegressionMethod:
model3 = LogisticRegressionModel(duration, \
Array[NumericalVariable]([ nutritio, agecat1, agecat3, alcohol, smoking ]), \
LogisticRegressionMethod.Nominal)
# Everything else is the same:
model3.Compute()
# There is a set of parameters for each level of the
# response variable. The highest level is the reference
# level and has no associated parameters.
for p in model3.Parameters:
print p.ToString()
print "Log likelihood: {0:.4f}".format(model3.GetLogLikelihood())
# To test the hypothesis that all the slopes are zero, # use the GetLikelihoodRatioTest method.
lrt = model3.GetLikelihoodRatioTest()
print "Test that all slopes are zero: chi-squared={0:.4f}, p={1:.4f}".format(lrt.Statistic, lrt.PValue)
```