-
-
Save alvations/b754bffe1dab515d9af7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import numpy as np | |
from sklearn.cross_validation import train_test_split | |
import xgboost as xgb | |
import operator | |
types = {'f1': np.dtype(float), 'f2': np.dtype(float), 'f3': np.dtype(float), 'f4': np.dtype(float), | |
'f5': np.dtype(float), 'f6': np.dtype(float), 'f7': np.dtype(float), 'f8': np.dtype(float), | |
'f9': np.dtype(float), 'f10': np.dtype(float), 'f11': np.dtype(float), 'f12': np.dtype(float), | |
'f13': np.dtype(float), 'f14': np.dtype(float), 'c1': np.dtype(str), 'validation': np.dtype(int), | |
'target': np.dtype(int)} | |
train_valid = pd.read_csv("numerai_training_data.csv",dtype=types) | |
mappings = {c:i for i, c in enumerate(pd.unique(train_valid.c1.ravel()))} | |
train_valid.c1.replace(mappings, inplace=True) | |
train = train_valid[train_valid['validation'] == 0] | |
valid = train_valid[train_valid['validation'] == 1] | |
params = {"objective": "binary:logistic", | |
"booster" : "gbtree", | |
"eta": 0.1, | |
"max_depth": 30, | |
"subsample": 0.9, | |
"colsample_bytree": 0.7, | |
"silent": 1, | |
"seed": 0, | |
'eval_metric': 'auc' | |
} | |
num_boost_round = 500 | |
features = ['f{}'.format(i) for i in range(1,15)] + ['c1'] | |
X_train, X_valid = train_test_split(train_valid, test_size=0.20, random_state=10) | |
#X_train, X_valid = train, valid # eval-auc:0.513770 | |
y_train = np.log1p(X_train.target) | |
y_valid = np.log1p(X_valid.target) | |
dtrain = xgb.DMatrix(X_train[features], y_train) | |
dvalid = xgb.DMatrix(X_valid[features], y_valid) | |
watchlist = [(dtrain, 'train'), (dvalid, 'eval')] | |
gbm = xgb.train(params, dtrain, num_boost_round, evals=watchlist, \ | |
early_stopping_rounds=100, verbose_eval=True) | |
print("Validating") | |
yhat = gbm.predict(xgb.DMatrix(X_valid[features])) | |
testtypes = {'f1': np.dtype(float), 'f2': np.dtype(float), 'f3': np.dtype(float), 'f4': np.dtype(float), | |
'f5': np.dtype(float), 'f6': np.dtype(float), 'f7': np.dtype(float), 'f8': np.dtype(float), | |
'f9': np.dtype(float), 'f10': np.dtype(float), 'f11': np.dtype(float), 'f12': np.dtype(float), | |
'f13': np.dtype(float), 'f14': np.dtype(float), 'c1': np.dtype(str), 't_id':np.dtype(str)} | |
test = pd.read_csv("numerai_tournament_data.csv",dtype=testtypes) | |
test.c1.replace(mappings, inplace=True) | |
dtest = xgb.DMatrix(test[features]) | |
test_probs = gbm.predict(dtest) | |
# Make Submission | |
result = pd.DataFrame({"t_id": test["t_id"], 'probability': np.expm1(test_probs)}) | |
result = result[['t_id', 'probability']] | |
result.to_csv("sub4.csv", index=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment