Python AllStateDataLoader.get_data_2_train Examples

Example #1

File: AllStateDataLoaderTest.py Project: mithunmanohar/kaggle

class AllStateDataLoaderTest(unittest.TestCase):
    def setUp(self):
        self.data_loader = AllStateDataLoader()

    def testColumnsData2Train(self):
        self.data_2_train = self.data_loader.get_data_2_train()
        self.assertTrue("real_A" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_2" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_2_0" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_3_0" in self.data_2_train.columns)

Example #2

File: AllStateDataLoaderTest.py Project: ageek/AllStateKaggle

class AllStateDataLoaderTest(unittest.TestCase):

    def setUp(self):
        self.data_loader = AllStateDataLoader()


    def testColumnsData2Train(self):
        self.data_2_train = self.data_loader.get_data_2_train()
        self.assertTrue("real_A" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_2" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_2_0" in self.data_2_train.columns)
        self.assertFalse("value_A_pt_3_0" in self.data_2_train.columns)

Example #3

File: predict_linearsvc_one_var_simple.py Project: ageek/AllStateKaggle

    return np.array(np.where(tmp["real_%s" % letter] == value, 1, 0))

def get_y(letter, data):

    tmp = data.copy()

    return np.array(tmp["real_%s" % letter])


from sklearn import svm
from sklearn.externals import joblib
from sklearn import grid_search

l = AllStateDataLoader()
print("Extraction data_2...")
data_2 = l.get_data_2_train()
print("Extraction data_3...")
data_3 = l.get_data_3_train()
print("Extraction data_4...")
data_4 = l.get_data_4_train()
print("Extraction data_all...")
data_all = l.get_data_all_train()

def fit_and_save_log(parameters, dataset, letter, filename,verbose=2):
    log = svm.LinearSVC(class_weight="auto")

    X = get_X_without_scaler(dataset)
    y = get_y(letter, dataset)

    model = grid_search.GridSearchCV(log, parameters, verbose=verbose)
    model.fit(X,y)

Example #4

File: predict_logistic_one_var.py Project: mithunmanohar/kaggle

def get_y(letter, data):

    tmp = data.copy()

    return np.array(tmp["real_%s" % letter])


from sklearn import linear_model
from sklearn.externals import joblib
from sklearn import grid_search

l = AllStateDataLoader()
print("Extraction data_2...")
data_2 = l.get_data_2_train()
print("Extraction data_3...")
data_3 = l.get_data_3_train()
print("Extraction data_all...")
data_all = l.get_data_all_train()


def fit_and_save_log(parameters, dataset, letter, filename, verbose=2):
    log = linear_model.LogisticRegression()

    X = get_X_without_scaler(dataset)
    y = get_y(letter, dataset)

    model = grid_search.GridSearchCV(log, parameters, verbose=verbose)
    model.fit(X, y)

Example #5

    return np.array(np.where(tmp["real_%s" % letter] == value, 1, 0))

def get_y(letter, data):

    tmp = data.copy()

    return np.array(tmp["real_%s" % letter])


from sklearn import svm
from sklearn.externals import joblib
from sklearn import grid_search

l = AllStateDataLoader()
print("Extraction data_2...")
data_2 = l.get_data_2_train(with_location_view=True)
print("Extraction data_3...")
data_3 = l.get_data_3_train(with_location_view=True)
print("Extraction data_4...")
data_4 = l.get_data_4_train(with_location_view=True)
print("Extraction data_all...")
data_all = l.get_data_all_train(with_location_view=True)

def fit_and_save_log(parameters, dataset, letter, filename,verbose=2):
    log = svm.LinearSVC(class_weight="auto")

    X = get_X_without_scaler(dataset)
    y = get_y(letter, dataset)

    model = grid_search.GridSearchCV(log, parameters, verbose=verbose)
    model.fit(X,y)