def Myprediction(df, features, clf, name, item_category_list_unique):
testdf = pd.read_csv('data/test/round1_ijcai_18_test_a_20180301.txt',
sep=' ')
testdf.context_timestamp += 8 * 60 * 60
testdf = convert_time(testdf)
testdf.item_category_list.replace(
item_category_list_unique,
list(np.arange(len(item_category_list_unique))),
inplace=True)
prediction_format = pd.read_csv('data/output/0203.txt', sep=' ')
train, predict = df, testdf
clf.fit(train[features],
train.is_trade,
eval_set=[(train[features], train.is_trade)],
eval_metric='logloss',
verbose=True)
predict['predicted_score'] = clf.predict_proba(predict[features])[:, 1]
print(predict[['instance_id', 'predicted_score']])
prediction_file = pd.merge(prediction_format[['instance_id']],
predict[['instance_id', 'predicted_score']],
on='instance_id',
how='left')
prediction_file.to_csv('data/output/{}.txt'.format(name),
sep=' ',
index=None)
return clf
def base_process(data):
lbl = preprocessing.LabelEncoder()
print(
'--------------------------------------------------------------item--------------------------------------------------------------'
)
data['len_item_category'] = data['item_category_list'].map(
lambda x: len(str(x).split(';')))
data['len_item_property'] = data['item_property_list'].map(
lambda x: len(str(x).split(';')))
for i in range(1, 3):
data['item_category_list' + str(i)] = lbl.fit_transform(
data['item_category_list'].map(lambda x: str(str(x).split(';')[i])
if len(str(x).split(';')) > i else
'')) # item_category_list的第0列全部都一样
for i in range(10):
data['item_property_list' + str(i)] = lbl.fit_transform(
data['item_property_list'].map(lambda x: str(str(x).split(';')[
i]) if len(str(x).split(';')) > i else ''))
for col in ['item_id', 'item_brand_id', 'item_city_id']:
data[col] = lbl.fit_transform(data[col])
print(
'--------------------------------------------------------------user--------------------------------------------------------------'
)
for col in ['user_id']:
data[col] = lbl.fit_transform(data[col])
print('user 0,1 feature')
data['gender0'] = data['user_gender_id'].apply(lambda x: 1
if x == -1 else 2)
data['age0'] = data['user_age_level'].apply(
lambda x: 1 if x == 1004 | x == 1005 | x == 1006 | x == 1007 else 2)
data['occupation0'] = data['user_occupation_id'].apply(
lambda x: 1 if x == -1 | x == 2003 else 2)
data['star0'] = data['user_star_level'].apply(
lambda x: 1 if x == -1 | x == 3000 | x == 3001 else 2)
print(
'--------------------------------------------------------------context--------------------------------------------------------------'
)
# data['realtime'] = data['context_timestamp'].apply(timestamp_datetime)
# data['realtime'] = pd.to_datetime(data['realtime'])
# data['day'] = data['realtime'].dt.day
# data['hour'] = data['realtime'].dt.hour
data = convert_time(data)
data['len_predict_category_property'] = data[
'predict_category_property'].map(lambda x: len(str(x).split(';')))
for i in range(5):
data['predict_category_property' + str(i)] = lbl.fit_transform(
data['predict_category_property'].map(lambda x: str(
str(x).split(';')[i]) if len(str(x).split(';')) > i else ''))
print('context 0,1 feature')
data['context_page0'] = data['context_page_id'].apply(
lambda x: 1
if x == 4001 | x == 4002 | x == 4003 | x == 4004 | x == 4007 else 2)
print(
'--------------------------------------------------------------shop--------------------------------------------------------------'
)
for col in ['shop_id']:
data[col] = lbl.fit_transform(data[col])
data['shop_score_delivery0'] = data['shop_score_delivery'].apply(
lambda x: 0 if x <= 0.98 and x >= 0.96 else 1)
return data
verbose=True)
predict['predicted_score'] = clf.predict_proba(predict[features])[:, 1]
print(predict[['instance_id', 'predicted_score']])
prediction_file = pd.merge(prediction_format[['instance_id']],
predict[['instance_id', 'predicted_score']],
on='instance_id',
how='left')
prediction_file.to_csv('data/output/{}.txt'.format(name),
sep=' ',
index=None)
return clf
df = pd.read_csv('data/train/round1_ijcai_18_train_20180301.txt', sep=' ')
df.context_timestamp += 8 * 60 * 60
df = convert_time(df)
item_category_list_unique = list(np.unique(df.item_category_list))
df.item_category_list.replace(item_category_list_unique,
list(np.arange(len(item_category_list_unique))),
inplace=True)
label = 'is_trade'
start_features = [
'item_category_list',
'item_city_id',
'item_price_level',
'item_sales_level',
'item_collected_level',
'item_pv_level',
'user_gender_id',
'user_age_level',