def train(self, ds):
datassc = ds[ds['StoreType_Shopping Center'] == 1]
datasoth = ds[ds['StoreType_Shopping Center'] == 0]
datasc = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datassc) \
.exclude('NumberOfSales', 'Month') \
.build()
print("SHOPPING CENTERS MODEL TRAINING: ")
for i in range(self.nsc):
print("SC :", i)
x, y = datasc.random_sampling(1.0)
mod = self.model_shopc()
mod.fit(x, y)
pr = mod.predict(datasc.xtr)
self.models_sc.append(mod)
print("SC ", i, " TRAIN R2: ", eval.evaluate(datasc.ytr, pr))
dataoth = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datasoth) \
.exclude('NumberOfSales', 'Month') \
.build()
print("OTHER SHOPS MODEL TRAINING: ")
for i in range(self.noth):
print("OTH :", i)
x, y = dataoth.random_sampling(1.0)
mod = self.model_others()
mod.fit(x, y)
pr = mod.predict(dataoth.xtr)
self.models_o.append(mod)
print("OTH ", i, " TRAIN R2: ", eval.evaluate(dataoth.ytr, pr))
def test(self, ds):
datassc = ds[ds['StoreType_Shopping Center'] == 1]
datasoth = ds[ds['StoreType_Shopping Center'] == 0]
datasc = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datassc) \
.exclude('NumberOfSales', 'Month') \
.build()
print("SHOPPING CENTERS MODEL EVALUATION")
preds = self.predict_sc(datasc.xts)
print("SC TEST R2: ", eval.evaluate(datasc.yts, preds))
dataoth = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datasoth) \
.exclude('NumberOfSales', 'Month') \
.build()
print("OTHERS MODEL EVALUATION")
preds = self.predict_oth(dataoth.xts)
print("OTH TEST R2: ", eval.evaluate(dataoth.yts, preds))
from numpy import loadtxt
from xgboost import XGBRegressor
from sklearn import linear_model
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
import dataset.setbuilder as sb
import models.sklearn.evaluator as eval
data = sb.SetBuilder(target='NumberOfCustomers',
autoexclude=True).exclude('NumberOfSales',
'Month').build()
model = XGBRegressor(n_estimators=100,
learning_rate=0.2,
colsample_bytree=1,
max_depth=4,
silent=False,
n_jobs=8)
model.fit(data.xtr, data.ytr)
pred_tr = model.predict(data.xtr)
pred_ts = model.predict(data.xts)
print('R2 TRAIN = %s' % eval.evaluate(data.ytr, pred_tr))
print('R2 TEST = %s' % eval.evaluate(data.yts, pred_ts))
'Month').build()
#data = sb.SetBuilder(target='NumberOfSales').exclude('Day').build()
nn = neural_network.MLPRegressor(hidden_layer_sizes=(100, 5),
activation='relu',
solver='adam',
batch_size='auto',
learning_rate='adaptive',
learning_rate_init=0.001,
max_iter=50,
shuffle=True,
random_state=9,
tol=0.000001,
verbose=True,
warm_start=False,
momentum=0.9,
nesterovs_momentum=True,
early_stopping=False,
validation_fraction=0.1,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08)
n = nn.fit(data.xtr, data.ytr.ravel())
ypred = nn.predict(data.xts)
ds.save_dataset(pd.DataFrame(ypred), 'customer_pred_jan_feb_NN.csv')
print('R2 = %s' % eval.evaluate(data.yts, ypred))
max_iter=50,
shuffle=True,
tol=0.000001,
verbose=True,
warm_start=False,
momentum=0.9,
nesterovs_momentum=True,
early_stopping=False,
validation_fraction=0.1,
beta_1=0.9,
beta_2=0.999,
epsilon=1e-08)
dt.fit(bagx, bagy.ravel())
models.append(dt)
y = dt.predict(data.xtr)
print('it = %s, TRAIN R2 = %s' % (i, eval.evaluate(data.ytr, y)))
yy.append(y)
yy = np.array(yy)
pred = yy.mean(axis=0)
print('Bagging R2 = %s' % eval.evaluate(data.ytr, pred))
re, totr, totp = ev_cust.region_error(data.ytr, pred, regions, ids, dates)
diff = totr - totp
print("REG_ERR: ", re * 100)
print("REG_MEAN_ERR: ", re.mean() * 100)
print("REAL_SUM: ", totr.sum())
print("PRED_SUM: ", totp.sum())
print("SUM_OF_DIFFS: ", diff.sum())
axis=1)).squeeze()
clean_row = clean_row.reshape([1, -1])
if sc:
return self.predict_sc(clean_row).squeeze()
else:
return self.predict_oth(clean_row).squeeze()
def model1():
return linear_model.Ridge(alpha=10)
def model2():
return tree.DecisionTreeRegressor(max_depth=9)
data = data_manager.read_dataset("best_for_customers.csv")
model = CustomersPredoctorSeparateShopCenters(model1, model1, 10, 10)
model.train(data)
model.test(data)
data = utils.get_frame_in_range(data, 1, 2018, 2, 2018)
preds = []
for i in range(len(data)):
irow = data.iloc[[i]]
preds.append(model.predict(irow))
preds = np.array(preds)
data = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=data) \
.exclude('NumberOfSales', 'Month') \
.build()
print("FINAL R2: ", eval.evaluate(data.yts, preds))
# data = sb.SetBuilder(target='NumberOfSales', autoexclude=True, dataset='mean_var_on_cust_from_tain.csv').build()
# Performs simple linear regression
depth = 8
dtree = tree.DecisionTreeRegressor(max_depth=depth)
dtree.fit(data.xtr, data.ytr)
ypred = dtree.predict(data.xts)
pr.save_model(dtree, 'decision_tree_cust')
dtree = pr.load_model('decision_tree_cust')
ypred = dtree.predict(data.xts)
print('R2 train = %s' % eval.evaluate(data.ytr, dtree.predict(data.xtr)))
print('R2 test = %s' % eval.evaluate(data.yts, ypred))
print("Plain Decision regression tree without bagging")
it = 10
yy = []
for i in range(it):
bagx, bagy = data.random_sampling(1)
dt = tree.DecisionTreeRegressor(max_depth=depth)
dt.fit(bagx, bagy)
pr.save_model(dt, 'dt_cust_bootstraping_%s' % i)
y = dt.predict(data.xts)
print('it = %s, R2 = %s' % (i, eval.evaluate(data.yts, y)))
yy.append(y)
yy = np.array(yy)
import dataset.setbuilder as sb
from sklearn import linear_model
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import models.sklearn.evaluator as eval
from sklearn.preprocessing import PolynomialFeatures
data = sb.SetBuilder(target="NumberOfSales",
dataset="final_for_sales_train.csv",
autoexclude=False,
split=[[(3, 2016, 1, 2018)], [(3, 2016, 2, 2018)]
]).only('NearestCompetitor').build()
poly_degree = 2
# Performs simple linear regression
print("Linear regression started, polynomial degree = %s" % poly_degree)
poly = PolynomialFeatures(degree=poly_degree)
xtr_ = poly.fit_transform(data.xtr)
xts_ = poly.fit_transform(data.xts)
model = linear_model.LinearRegression()
model.fit(data.xtr, data.ytr)
print(eval.evaluate(data.ytr, model.predict(data.xtr)))
print(eval.evaluate(data.yts, model.predict(data.xts)))
print(model.coef_)
print(model.intercept_)