-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcatboost_online.py
154 lines (130 loc) · 4.65 KB
/
catboost_online.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
# -*- coding: utf-8 -*-
"""
Created on Mon Oct 2 09:32:30 2017
@author: darshan
"""
import pandas as pd
import numpy as np
from catboost import CatBoostRegressor
from tqdm import tqdm
print("\nReading data.....")
train_df = pd.read_csv('train_2016_v2.csv', parse_dates=['transactiondate'], low_memory=False)
test_df = pd.read_csv('sample_submission.csv', low_memory=False)
properties = pd.read_csv('properties_2016.csv', low_memory=False)
# field is named differently in submission
test_df['parcelid'] = test_df['ParcelId']
# similar to the1owl
def add_date_features(df):
df["transaction_year"] = df["transactiondate"].dt.year
df["transaction_month"] = df["transactiondate"].dt.month
df["transaction_day"] = df["transactiondate"].dt.day
df["transaction_quarter"] = df["transactiondate"].dt.quarter
df.drop(["transactiondate"], inplace=True, axis=1)
return df
print("\nProcessing data.....")
train_df = add_date_features(train_df)
train_df = train_df.merge(properties, how='left', on='parcelid')
test_df = test_df.merge(properties, how='left', on='parcelid')
print("Train: ", train_df.shape)
print("Test: ", test_df.shape)
print("\nRemoving missing data fields.......")
missing_perc_thresh = 0.98
exclude_missing = []
num_rows = train_df.shape[0]
for c in train_df.columns:
num_missing = train_df[c].isnull().sum()
if num_missing == 0:
continue
missing_frac = num_missing / float(num_rows)
if missing_frac > missing_perc_thresh:
exclude_missing.append(c)
print("We exclude: %s" % exclude_missing)
print(len(exclude_missing))
print("\nRemoving datafields with same datavalues.....")
# exclude where we only have one unique value :D
exclude_unique = []
for c in train_df.columns:
num_uniques = len(train_df[c].unique())
if train_df[c].isnull().sum() != 0:
num_uniques -= 1
if num_uniques == 1:
exclude_unique.append(c)
print("We exclude: %s" % exclude_unique)
print(len(exclude_unique))
print("\nDefining training features....")
exclude_other = ['parcelid', 'logerror'] # for indexing/training only
# do not know what this is LARS, 'SHCG' 'COR2YY' 'LNR2RPD-R3' ?!?
exclude_other.append('propertyzoningdesc')
train_features = []
for c in train_df.columns:
if c not in exclude_missing \
and c not in exclude_other and c not in exclude_unique:
train_features.append(c)
print("We use these for training: %s" % train_features)
print(len(train_features))
print("\nDefining what features are categorical.....")
cat_feature_inds = []
cat_unique_thresh = 1000
for i, c in enumerate(train_features):
num_uniques = len(train_df[c].unique())
if num_uniques < cat_unique_thresh \
and not 'sqft' in c \
and not 'cnt' in c \
and not 'nbr' in c \
and not 'number' in c:
cat_feature_inds.append(i)
print("Cat features are: %s" % [train_features[ind] for ind in cat_feature_inds])
print("\nFilling missing values in data....")
# some out of range int is a good choice
train_df.fillna(-999, inplace=True)
test_df.fillna(-999, inplace=True)
print("Shape of the data.....")
X_train = train_df[train_features]
y_train = train_df.logerror
print("\nTraining data size:")
print(X_train.shape, y_train.shape)
print("Testing data size:")
test_df['transactiondate'] = pd.Timestamp('2016-12-01') # Dummy
test_df = add_date_features(test_df)
X_test = test_df[train_features]
print(X_test.shape)
print("\nTraining & Testing model......")
num_ensembles = 5
y_pred = 0.0115
for i in tqdm(range(num_ensembles)):
# TODO(you): Use CV, tune hyperparameters
model = CatBoostRegressor(
iterations=350, learning_rate=0.07,
depth=6, l2_leaf_reg=3,
loss_function='MAE',
eval_metric='MAE',
random_seed=i)
model.fit(
X_train, y_train,
cat_features=cat_feature_inds)
y_pred += model.predict(X_test)
y_pred /= num_ensembles
print("\nLoading results into csv....")
submission = pd.DataFrame({
'ParcelId': test_df['parcelid'],
})
test_dates = {
'201610': pd.Timestamp('2016-09-30'),
'201611': pd.Timestamp('2016-10-31'),
'201612': pd.Timestamp('2016-11-30'),
'201710': pd.Timestamp('2017-09-30'),
'201711': pd.Timestamp('2017-10-31'),
'201712': pd.Timestamp('2017-11-30')
}
for label, test_date in test_dates.items():
print("Predicting for: %s ... " % (label))
# TODO(you): predict for every `test_date`
submission[label] = y_pred
submission_major = 387
submission.to_csv(
'catboost_%03d.csv' % (submission_major),
float_format='%.4f',
index=False)
print("Done! Good luck with submission #%d :)" % submission_major)
#Credits:
#https://www.kaggle.com/seesee/concise-catboost-starter-ensemble-plb-0-06435