# Isaac Li
# 1.23.2018
import time
import numpy as np
from sklearn.model_selection import KFold
from sklearn.metrics import mean_squared_error
import function
train, test = function.read_file(path='a')
train["血糖"] = np.log1p(train["血糖"])
train, test = function.add_column(train, test)
train, test = function.transform(train, test)
print('\n\nStart...')
t0, mses = time.time(), []
train_preds, test_preds = np.zeros(train.shape[0]), np.zeros((test.shape[0], 5))
predictors = [f for f in test.columns if f not in ['血糖']]
kf = KFold(n_splits=5, shuffle=True, random_state=520)
for i, (train_index, test_index) in enumerate(kf.split(train)):
print(' .{}/5.'.format(i + 1))
train_feat1, train_feat2 = train.iloc[train_index], train.iloc[test_index]
gbm = function.settings.model_lgb.fit(train_feat1[predictors], train_feat1['血糖'],
categorical_feature=['性别', '体检日期'])
predict = gbm.predict(train_feat2[predictors])
train_preds[test_index] += predict
mses.append(.5 * mean_squared_error(np.expm1(train_feat2['血糖']), np.expm1(predict)))
test_preds[:, i] = gbm.predict(test[predictors])
cv = .5 * mean_squared_error(np.expm1(train['血糖']), np.expm1(train_preds))
ans_path = function.settings.source_path + 'd_answer_a_20180128.csv'
ans = pd.read_csv(ans_path,
encoding='gbk') # NOTICE: add a row in file as index!
# ------------ predict a -----------------------------------------------------------------------------------------------
a = input('Part A? -> ')
if a:
print('Done.')
else:
print('Part A.')
train, test = train_a, test_a
train["血糖"] = np.log1p(train["血糖"])
if not s:
list_test = function.settings.all_items + ['其他胆固醇']
train, test = function.add_column(train, test, test_item=list_test[3:])
else:
train, test = function.add_column(train, test)
train, test = function.transform(train, test)
print('\n\nStart...')
t0, mses = time.time(), []
train_preds, test_preds = np.zeros(train.shape[0]), np.zeros(
(test.shape[0], 5))
predictors = [f for f in test.columns if f not in ['血糖']]
kf = KFold(n_splits=5, shuffle=True, random_state=520)
for i, (train_index, test_index) in enumerate(kf.split(train)):
print(' .{}/5.'.format(i + 1))
train_feat1, train_feat2 = train.iloc[train_index], train.iloc[
test_index]
# Isaac Li
# 1.23.2018
import time
import numpy as np
from sklearn.model_selection import KFold
from sklearn.metrics import mean_squared_error
import function
train, test = function.read_file()
train["血糖"] = np.log1p(train["血糖"])
train, test = function.add_column(train, test, sqrt=True)
train, test = function.transform(train, test)
print('\n\nStart...')
t0, mses = time.time(), []
train_preds, test_preds = np.zeros(train.shape[0]), np.zeros(
(test.shape[0], 5))
predictors = [f for f in test.columns if f not in ['血糖']]
kf = KFold(n_splits=5, shuffle=True, random_state=520)
for i, (train_index, test_index) in enumerate(kf.split(train)):
print(' .{}/5.'.format(i + 1))
train_feat1, train_feat2 = train.iloc[train_index], train.iloc[test_index]
gbm = function.settings.model_lgb.fit(train_feat1[predictors],
train_feat1['血糖'],
categorical_feature=['性别', '体检日期'])
predict = gbm.predict(train_feat2[predictors])
train_preds[test_index] += predict
mses.append(
.5 *
# Isaac Li
# 1.23.2018
import time
import numpy as np
from sklearn.model_selection import KFold
from sklearn.metrics import mean_squared_error
import function
train, test = function.read_file(path='s')
train["血糖"] = np.log1p(train["血糖"])
train, test = function.add_column(train,
test,
test_item=function.settings.all_items[3:] +
['其他胆固醇'])
train, test = function.transform(train, test)
print('\n\nStart...')
t0, mses = time.time(), []
train_preds, test_preds = np.zeros(train.shape[0]), np.zeros(
(test.shape[0], 5))
predictors = [f for f in test.columns if f not in ['血糖']]
kf = KFold(n_splits=5, shuffle=True, random_state=520)
for i, (train_index, test_index) in enumerate(kf.split(train)):
print(' .{}/5.'.format(i + 1))
train_feat1, train_feat2 = train.iloc[train_index], train.iloc[test_index]
gbm = function.settings.model_lgb.fit(train_feat1[predictors],
train_feat1['血糖'],
categorical_feature=['性别', '体检日期'])
predict = gbm.predict(train_feat2[predictors])
# Isaac Li
# 1.23.2018
import time
import numpy as np
from sklearn.model_selection import KFold
from sklearn.metrics import mean_squared_error
import function
train, test = function.read_file()
train["血糖"] = np.log1p(train["血糖"])
train, test = function.add_column(train, test, sqrt=True, power3_a=True)
train, test = function.transform(train, test)
print('\n\nStart...')
t0, mses = time.time(), []
train_preds, test_preds = np.zeros(train.shape[0]), np.zeros(
(test.shape[0], 5))
predictors = [f for f in test.columns if f not in ['血糖']]
kf = KFold(n_splits=5, shuffle=True, random_state=520)
for i, (train_index, test_index) in enumerate(kf.split(train)):
print(' .{}/5.'.format(i + 1))
train_feat1, train_feat2 = train.iloc[train_index], train.iloc[test_index]
gbm = function.settings.model_lgb.fit(train_feat1[predictors],
train_feat1['血糖'],
categorical_feature=['性别', '体检日期'])
predict = gbm.predict(train_feat2[predictors])
base, power, minimum = 1.7, 1, 7