def fit(self):
for i in range(self.count):
x_sampled, y_sampled = self.training_ds.random_sampling(1.0)
curr = tree.DecisionTreeRegressor()
curr.fit(x_sampled, y_sampled)
tr_predictions = curr.predict(self.training_ds.xtr)
self.training_predictions.append(tr_predictions)
print("Model %s :: Sales R2 on training set: %s" %
(i, eval.r2_score(self.training_ds.ytr, tr_predictions)))
ts_predictions = curr.predict(self.testing_ds.xts)
self.predictions.append(ts_predictions)
# We cannot evaluate our predictions when building the final model, we don't have a test set :)
# print("Customer R2 on testing set: ", eval.r2_score(self.ds.yts, ts_predictions))
self.save_partial(curr, i)
self.compute_final_predictions()
print("Overall sales R2 on training set: %s" % eval.r2_score(
self.training_ds.ytr, self.final_training_predictions))
print(
"Done with sales bagging, models have been saved in 'saved' dir.")
print("When ready, execute save_predictions.")
def fit(self):
for i in range(self.count):
x_sampled, y_sampled = self.training_ds.random_sampling(1.0)
curr = skc.LinearSklearn(1, CustomerModel.model)
curr.train(x_sampled, y_sampled)
tr_predictions = curr.predict(self.training_ds.xtr).squeeze()
self.training_predictions.append(tr_predictions)
print("Model %s :: Customer R2 on training set: %s" %
(i, eval.r2_score(self.training_ds.ytr, tr_predictions)))
ts_predictions = curr.predict(self.testing_ds.xts)
self.predictions.append(ts_predictions)
# We cannot evaluate our predictions when building the final model, we don't have a test set :)
# print("Customer R2 on testing set: ", eval.r2_score(self.ds.yts, ts_predictions))
self.save_partial(curr, i)
self.compute_final_predictions()
print("Overall customer R2 on training set: %s" % eval.r2_score(
self.training_ds.ytr, self.final_training_predictions))
print(
"Done with customer bagging, models have been saved in 'saved' dir."
)
print("When ready, execute save_predictions.")
]:
cols.remove(att)
datas = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datas)\
.exclude('NumberOfSales', 'Month')\
.build()
n = 1
mods = []
for i in range(n):
print(i + 1)
x, y = datas.random_sampling(1.0)
mod = skc.LinearSklearn(1, model)
mod.train(x, y)
mods.append(mod)
p = mod.predict(x).squeeze()
print("TRAIN R2: ", eval.r2_score(y, p))
print("TEST R2: ", eval.r2_score(datas.yts, mod.predict(datas.xts)))
print("##########################")
#tree.export_graphviz(mod.models[0])
#print("SAVED")
preds = []
for i in range(n):
preds.append(mods[i].predict(datas.xts))
custpred = np.array(preds).mean(axis=0)
print("TEST R2: ", eval.r2_score(datas.yts, custpred))
print("############################################")
for i in range(n):
for j in range(len(cols)):
n = len(model)
mods = []
modpreds = []
modpreds_t = []
for i in range(n):
print(i + 1)
x, y = datas.xtr, datas.ytr
mod = skc.LinearSklearn(1, model[i])
mod.train(x, y)
mods.append(mod)
p = mod.predict(x).squeeze()
print(p)
p_t = mod.predict(datas.xts).squeeze()
modpreds.append(p)
modpreds_t.append(p_t)
print("TRAIN R2: ", eval.r2_score(y, p))
print("TEST R2: ", eval.r2_score(datas.yts, p_t))
print("##########################")
modpreds = np.array(modpreds).transpose()
modpreds_t = np.array(modpreds_t).transpose()
x = np.hstack((datas.xtr, modpreds))
x_t = np.hstack((datas.xts, modpreds_t))
fin = skc.LinearSklearn(1, final)
fin.train(x, datas.ytr)
custpred = fin.predict(x_t)
print(custpred)
print("TEST R2: ", eval.r2_score(datas.yts, custpred))
new = pandas.DataFrame()
datas, utils.get_frame_in_range(datas, 3, 2016, 12, 2017))
datas = preu.mean_cust_per_shop_if_holiday(
datas, utils.get_frame_in_range(datas, 3, 2016, 12, 2017))
datas = sb.SetBuilder(target='NumberOfCustomers', autoexclude=True, df=datas)\
.exclude('NumberOfSales', 'Month')\
.build()
n = 10
mods = []
for i in range(n):
print(i + 1)
x, y = datas.random_sampling(1.0)
mod = skc.LinearSklearn(1, model)
mod.train(x, y)
mods.append(mod)
p = mod.predict(x).squeeze()
print("TRAIN R2: ", eval.r2_score(y, p))
print("TEST R2: ", eval.r2_score(datas.yts, mod.predict(datas.xts)))
print("##########################")
preds = []
for i in range(n):
preds.append(mods[i].predict(datas.xtr))
trainpreds = np.array(preds).mean(axis=0).squeeze()
preds = []
for i in range(n):
preds.append(mods[i].predict(datas.xts))
custpred = np.array(preds).mean(axis=0).squeeze()
print("TYPE " + str(i))
d_reg = utils.get_frames_per_assortmenttype(train, i)
d_reg_t = utils.get_frames_per_assortmenttype(test, i)
print("N_SAMPLES: ", len(d_reg) + len(d_reg_t))
if len(d_reg) == 0:
continue
y = prepare_out(d_reg)
x = drop_useless(d_reg, 1)
y_t = prepare_out(d_reg_t)
x_t = drop_useless(d_reg_t, 1)
mod = skc.LinearSklearn(1, model)
mod.train(x, y)
models[i] = mod
p = mod.predict(x).squeeze()
pt = mod.predict(x_t).squeeze()
r2_t = eval.r2_score(y_t, pt)
sum += r2_t * (len(d_reg) + len(d_reg_t))
print("TRAIN R2: ", eval.r2_score(y, p))
print("TEST R2: ", r2_t)
print("##########################")
print("AVG TEST R2: ", sum / len(datas))
custpred = []
for i in test.index.tolist():
row = test.loc[i]
val = ""
for t in types:
if row[t] == 1:
val = t
row = drop_useless(row).reshape([1, -1])
from sklearn.neighbors import KNeighborsRegressor as knn
from sklearn import preprocessing
import pandas as pd
def model():
return knn(n_neighbors=10,
weights='uniform',
algorithm='ball_tree',
leaf_size=15)
if __name__ == '__main__':
datas = ds.read_dataset("best_for_customers.csv")
datas = sb.SetBuilder(target='NumberOfCustomers',
autoexclude=True,
df=datas).exclude('NumberOfSales', 'Month').build()
mod = skc.LinearSklearn(1, model)
x = datas.xtr
y = datas.ytr
mod.train(x, y)
custpred = mod.predict(datas.xts)
print("TEST R2: ", eval.r2_score(datas.yts, custpred))
print("##########################")
new = pandas.DataFrame()
new['NumberOfCustomers'] = pandas.Series(custpred)
ds.save_dataset(new, "knncustpreds1.csv")
