def main():
trainData = pd.read_csv("CrimeClassification/Dataset/train-2.csv")
trainData.info()
classesMap = dm.mapClasses(trainData)
cleanedTrainData = dm.cleanData(trainData, classesMap)
cleanedTrainData.describe()
heatMapXY(cleanedTrainData, "Global heatMap of crimes")
heatMapPerCategory(cleanedTrainData, classesMap)
histogramOfCategories(cleanedTrainData, classesMap)
textHistogram(cleanedTrainData, classesMap)
def main():
trainData = pd.read_csv("CrimeClassification/Dataset/train-2.csv")
classesMap = dm.mapClasses(trainData)
print trainData.info()
print (classesMap)
cleanedTrainData = dm.cleanData(trainData, classesMap)
testData = pd.read_csv("CrimeClassification/Dataset/test-2.csv")
cleanedTestData = dm.cleanTestData(testData)
print (cleanedTrainData.info())
model = trainModel(cleanedTrainData.values)
result = np.c_[cleanedTestData.values[:, 0].astype(int), output]
outputVec = sorted(classesMap, key=classesMap.__getitem__)
outputVec.insert(0, "Id")
dataFrameResults = pd.DataFrame(result, columns=outputVec)
dataFrameResults["Id"] = dataFrameResults["Id"].astype(int)
dm.saveResults(dataFrameResults)
def main():
pd.set_option("display.precision",3)
trainData = pd.read_csv('CrimeClassification/Dataset/train01-tsc.csv')
classesMap = dm.mapClasses(trainData)
print(classesMap)
cleanedTrainData = dm.cleanData(trainData,classesMap)
testData = pd.read_csv('CrimeClassification/Dataset/test-tsc.csv')
cleanedTestData = dm.cleanTestData(testData)
print(cleanedTrainData.info())
model = trainModel(cleanedTrainData.values)
print(cleanedTestData.info())
output = testProbaModel(model,cleanedTestData.values)
result = np.c_[cleanedTestData.values[:,0].astype(int),output]
outputVec = sorted(classesMap, key=classesMap.__getitem__)
outputVec.insert(0,'Id')
dataFrameResults = pd.DataFrame(result,columns=outputVec)
dataFrameResults['Id']=dataFrameResults['Id'].astype(int)
