__author__ = 'kunal' import csv from sklearn.ensemble import RandomForestClassifier as rfc import auxiliary trainDf = auxiliary.initialise_train(False) # auxiliary.computeMean(Category) # select all columns except # Dates,Category,Descript,DayOfWeek,PdDistrict,Resolution,Address,X,Y,Year,Week,Hour trainDf = trainDf.drop(['Dates', 'Descript', 'Resolution', 'Address'], axis=1) # Test data testDf = auxiliary.initialise_test(False) ids = testDf['Id'].values # Id,Dates,DayOfWeek,PdDistrict,Address,X,Y,Year,Week,Hour testDf = testDf.drop(['Id', 'Dates', 'Address'], axis=1) # Random Forest Algorithm print list(trainDf.columns.values) print list(testDf.columns.values) #print list(trainDf.X.values) # back to numpy format trainData = trainDf.values testData = testDf.values print 'Training...' forest = rfc(n_estimators=25) forest = forest.fit(trainData[0::,1::], trainData[0::,0])
from sklearn.feature_selection import f_classif, SelectKBest
from sklearn.feature_selection import RFE
from sklearn.linear_model import LogisticRegression
import matplotlib.pyplot as plt
from sklearn.ensemble import AdaBoostClassifier
warnings.simplefilter('ignore', DeprecationWarning)
warnings.simplefilter('ignore', UserWarning)
warnings.simplefilter('ignore', Warning)
trainDf = auxiliary.initialise_train(True)
trainDf = trainDf.drop(['Descript', 'Resolution', 'Address', 'Dates'], axis=1)
X, y = train_test_split(trainDf, train_size=.75)
# Test data
testDf = auxiliary.initialise_test(True)
ids = testDf['Id'].values
testDf = testDf.drop(['Id', 'Address', 'Dates'], axis=1)
# Attributes used in the model
print list(trainDf.columns.values)
print list(testDf.columns.values)
# back to numpy format
trainData = trainDf.values
testData = testDf.values
# Feature Selection:
# The Recursive Feature Elimination (RFE) method is a feature selection approach. It works by recursively removing
# attributes and building a model on those attributes that remain. It uses the model accuracy to identify which
# attributes (and combination of attributes) contribute the most to predicting the target attribute.
import csv
from sklearn.linear_model import LogisticRegression as lr
import auxiliary
import expolatory_graphs
trainDf = auxiliary.initialise_train(False)
# select all columns except
# Dates,Category,Descript,DayOfWeek,PdDistrict,Resolution,Address,X,Y,Year,Week,Hour
trainDf = trainDf.drop(
['Dates', 'Descript', 'DayOfWeek', 'Resolution', 'Address'], axis=1)
# Test data
testDf = auxiliary.initialise_test(False)
ids = testDf['Id'].values
# Id,Dates,DayOfWeek,PdDistrict,Address,X,Y,Year,Week,Hour
testDf = testDf.drop(['Id', 'Dates', 'Address', 'DayOfWeek'], axis=1)
# Random Forest Algorithm
print list(trainDf.columns.values)
print list(testDf.columns.values)
#print list(trainDf.X.values)
# back to numpy format
trainData = trainDf.values
testData = testDf.values
print 'Training...'
logit = lr()
logit = logit.fit(trainData[0::, 1::], trainData[0::, 0])