dtypes = {
'ip': 'uint32',
'app': 'uint16',
'device': 'uint16',
'os': 'uint16',
'channel': 'uint16',
'is_attributed': 'uint8',
'click_id': 'uint32'
}
import feature_engineerer
import gc
train_df = pd.read_csv('../input/train.csv', nrows=1000 * 100, dtype=dtypes)
feature_engineerer.do_feature_engineering(train_df)
len_train = len(train_df)
val_df = train_df[(len_train - 300000):len_train]
train_df = train_df[:(len_train - 300000)]
target = 'is_attributed'
predictors = ['app', 'device', 'os', 'channel', 'hour', 'hourly_click_count']
categorical = ['app', 'device', 'os', 'channel', 'hour']
print("Training...")
params = {
'learning_rate': 0.1,
#'is_unbalance': 'true', # replaced with scale_pos_weight argument
'num_leaves': 1400, # we should let it be smaller than 2^(max_depth)
'max_depth': 3, # -1 means no limit
'min_child_samples':
import pandas as pd
import feature_engineerer
train = pd.read_csv('../input/train_first_1000k.csv')
feature_engineerer.do_feature_engineering(train)
print(train.describe())
print(train["ip"].nunique())
exit(0)
train.to_csv("../output/engineered_first_1000k.csv",
float_format='%.6f',
index=False)
import pandas as pd
import csv_loader
import feature_engineerer
dtypes = csv_loader.get_dtypes()
df = pd.read_csv('../input/test.csv', dtype=dtypes, nrows=100000)
feature_engineerer.do_feature_engineering(df)
print(df.head())
df.to_csv("../output/checking.csv", index=False)
import pandas as pd
import numpy as np
import pocket_lgb
from sklearn import model_selection
import feature_engineerer
import holdout_validator
import csv_loader
dtypes = csv_loader.get_dtypes()
input_df = pd.read_csv('../input/train_day3.csv', nrows=1000000, dtype=dtypes)
feature_engineerer.do_feature_engineering(input_df)
print(input_df.describe())
split_number = 5
skf = model_selection.KFold(n_splits=split_number)
lgb = pocket_lgb.GoldenLgb()
first_model = None
total_score = 0
for train_index, test_index in skf.split(input_df):
train_np = input_df.iloc[train_index]
test_np = input_df.iloc[test_index]
train_df = pd.DataFrame(train_np)
test_df = pd.DataFrame(test_np)
model = lgb.do_train(train_df, test_df)
score = model.best_score["valid_0"]["auc"]
total_score += score
if first_model is None:
first_model = model
import pandas as pd
import feature_engineerer
import csv_loader
predictors = ['app', 'device', 'os', 'channel', 'hour', 'hourly_click_count']
categorical = ['app', 'device', 'os', 'channel', 'hour']
dtypes = csv_loader.get_dtypes()
test = pd.read_csv('../input/test.csv', dtype=dtypes, nrows=10000)
print(test.describe())
feature_engineerer.do_feature_engineering(test)
print(test.describe())
wtf = test[predictors]
print(wtf.describe())