def data_v6(data):
def get_y():
return data.get('train', 'y')
def get_X(dset='train'):
return data.extract(dset, [
('nums', None),
('cats', None),
('nans', None),
]).fillna(-999)
# 0.46007
model = skl.ensemble.ExtraTreesClassifier(n_estimators=1000,
criterion='entropy',
min_samples_leaf=5,
max_features=0.8,
n_jobs=8,
random_state=42)
X, y = get_X(), get_y()
X_test = get_X('test')
cv = skl.cross_validation.StratifiedKFold(y,
n_folds=16,
shuffle=True,
random_state=1234)
data.get('train', 'models')['draft_ext'] = model_train_cv_parallel(
model, X, y, n_jobs=1, cv=cv)['predict'] - 0.5
model.fit(X, y)
data.get('test',
'models')['draft_ext'] = model.predict_proba(X_test)[:, 1] - 0.5
def data_v30(data):
scaler = skl.preprocessing.StandardScaler()
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
X = data.extract(dset, [
('match', ['lobby_type_practice']),
('models', ['time_xgb']),
('synergy_sum', None),
('item_counts', None),
('ability_counts', None),
('team_diffs', ['first_ward']),
('fb', ['first_blood_team']),
('gold_counts', None),
('xp_counts', None),
('lh_counts', None),
('kills_counts', None),
]).to_sparse(0)
scale = ['time_xgb', 'anti_synergy', 'synergy']
X[scale] = scaler.fit_transform(X[scale]) if dset == 'train' else scaler.transform(X[scale])
return X
model = skl.linear_model.LogisticRegression(random_state=1234, C=0.005)
X, y = get_X(), get_y()
data.get('train', 'models')['common_linear'] = model_train_cv_parallel(model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['common_linear'] = model.predict_proba(get_X('test'))[:, 1] - 0.5
def data_v5(data):
def get_y():
return data.get('train', 'y')
def get_X(dset='train'):
return data.extract(dset, [
('nums', None),
('cats', None),
('nans', None),
]).fillna(-999)
# 0.46394
model = LogisticXGB(n_estimators=350,
learning_rate=0.05,
max_depth=7,
seed=42)
X, y = get_X(), get_y()
X_test = get_X('test')
cv = skl.cross_validation.StratifiedKFold(y,
n_folds=16,
shuffle=True,
random_state=1234)
data.dset('train')['models'] = pd.DataFrame(index=X.index)
data.get('train', 'models')['draft_xgb'] = model_train_cv_parallel(
model, X, y, n_jobs=1, cv=cv)['predict'] - 0.5
model.fit(X, y)
data.dset('test')['models'] = pd.DataFrame(index=X_test.index)
data.get('test',
'models')['draft_xgb'] = model.predict_proba(X_test)[:, 1] - 0.5
def data_v31(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('match', ['lobby_type_practice']),
('models', ['time_xgb']),
('synergy_sum', None),
('item_counts', None),
('ability_counts', None),
('team_diffs', ['first_ward']),
('fb', ['first_blood_team']),
('gold_counts', None),
('xp_counts', None),
('lh_counts', None),
('kills_counts', None),
('hero_roles_bag', None),
]).to_sparse(0)
model = LogisticXGB(n_estimators=500, learning_rate=0.1, max_depth=4, subsample=0.8, colsample_bytree=0.6, max_delta_step=1, seed=1234)
X, y = get_X(), get_y()
data.get('train', 'models')['common_xgb'] = model_train_cv_parallel(model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['common_xgb'] = model.predict_proba(get_X('test'))[:, 1] - 0.5
def data_v32(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('match', ['lobby_type_practice']),
('models', [
'time_xgb', 'pre_match_linear', 'pre_match_xgb',
'common_linear', 'common_xgb'
]),
]).to_sparse(0)
model = LogisticXGB(n_estimators=300,
learning_rate=0.01,
max_depth=4,
max_delta_step=1,
seed=1234)
X, y = get_X(), get_y()
data.get('train', 'models')['ensemble1_xgb'] = model_train_cv_parallel(
model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['ensemble1_xgb'] = model.predict_proba(
get_X('test'))[:, 1] - 0.5
def data_v31(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('match', ['lobby_type_practice']),
('models', ['time_xgb']),
('synergy_sum', None),
('item_counts', None),
('ability_counts', None),
('team_diffs', ['first_ward']),
('fb', ['first_blood_team']),
('gold_counts', None),
('xp_counts', None),
('lh_counts', None),
('kills_counts', None),
('hero_roles_bag', None),
]).to_sparse(0)
model = LogisticXGB(n_estimators=500,
learning_rate=0.1,
max_depth=4,
subsample=0.8,
colsample_bytree=0.6,
max_delta_step=1,
seed=1234)
X, y = get_X(), get_y()
data.get('train', 'models')['common_xgb'] = model_train_cv_parallel(
model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['common_xgb'] = model.predict_proba(
get_X('test'))[:, 1] - 0.5
def data_v25(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('models', ['time_xgb']), ('synergy_sum', None),
('hero_roles_bag', None),
('match',
['lobby_type_practice', 'lobby_type_public', 'lobby_type_ranked'])
])
model = LogisticXGB(n_estimators=100,
learning_rate=0.03,
max_depth=4,
subsample=0.8,
colsample_bytree=0.8,
seed=1234,
nthread=1)
X, y = get_X(), get_y()
data.get('train', 'models')['pre_match_xgb'] = model_train_cv_parallel(
model, X, y)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['pre_match_xgb'] = model.predict_proba(
get_X('test'))[:, 1] - 0.5
def data_v23(data):
model = LogisticXGB(n_estimators=2, max_depth=6, learning_rate=0.001, nthread=1)
X = data.get('train', 'match')[['start_time']]
y = data.get('train', 'y')
train_models = pd.DataFrame(index=X.index)
train_models['time_xgb'] = model_train_cv_parallel(model, X, y)['predict'] - 0.5
data.dset('train')['models'] = train_models
X_test = data.get('test', 'match')[['start_time']]
test_models = pd.DataFrame(index=X_test.index)
model.fit(X, y)
test_models['time_xgb'] = model.predict_proba(X_test)[:, 1] - 0.5
data.dset('test')['models'] = test_models
def data_v32(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('match', ['lobby_type_practice']),
('models', ['time_xgb', 'pre_match_linear', 'pre_match_xgb', 'common_linear', 'common_xgb']),
]).to_sparse(0)
model = LogisticXGB(n_estimators=300, learning_rate=0.01, max_depth=4, max_delta_step=1, seed=1234)
X, y = get_X(), get_y()
data.get('train', 'models')['ensemble1_xgb'] = model_train_cv_parallel(model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['ensemble1_xgb'] = model.predict_proba(get_X('test'))[:, 1] - 0.5
def data_v23(data):
model = LogisticXGB(n_estimators=2,
max_depth=6,
learning_rate=0.001,
nthread=1)
X = data.get('train', 'match')[['start_time']]
y = data.get('train', 'y')
train_models = pd.DataFrame(index=X.index)
train_models['time_xgb'] = model_train_cv_parallel(model, X,
y)['predict'] - 0.5
data.dset('train')['models'] = train_models
X_test = data.get('test', 'match')[['start_time']]
test_models = pd.DataFrame(index=X_test.index)
model.fit(X, y)
test_models['time_xgb'] = model.predict_proba(X_test)[:, 1] - 0.5
data.dset('test')['models'] = test_models
def data_v25(data):
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('models', ['time_xgb']),
('synergy_sum', None),
('hero_roles_bag', None),
('match', ['lobby_type_practice', 'lobby_type_public', 'lobby_type_ranked'])
])
model = LogisticXGB(n_estimators=100, learning_rate=0.03, max_depth=4, subsample=0.8, colsample_bytree=0.8, seed=1234, nthread=1)
X, y = get_X(), get_y()
data.get('train', 'models')['pre_match_xgb'] = model_train_cv_parallel(model, X, y)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['pre_match_xgb'] = model.predict_proba(get_X('test'))[:, 1] - 0.5
def data_v24(data):
scaler = skl.preprocessing.StandardScaler()
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('models', ['time_xgb']),
('synergy_sum', None),
('hero_roles_bag', None),
('match', ['lobby_type_practice', 'lobby_type_public', 'lobby_type_ranked'])
], scaler=scaler)
model = skl.linear_model.LogisticRegression(random_state=123, C=0.001)
X, y = get_X(), get_y()
data.get('train', 'models')['pre_match_linear'] = model_train_cv_parallel(model, X, y)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['pre_match_linear'] = model.predict_proba(get_X('test'))[:, 1] - 0.5
def data_v6(data):
def get_y():
return data.get('train', 'y')
def get_X(dset='train'):
return data.extract(dset, [
('nums', None),
('cats', None),
('nans', None),
]).fillna(-999)
# 0.46007
model = skl.ensemble.ExtraTreesClassifier(n_estimators=1000, criterion='entropy', min_samples_leaf=5, max_features=0.8, n_jobs=8, random_state=42)
X, y = get_X(), get_y()
X_test = get_X('test')
cv = skl.cross_validation.StratifiedKFold(y, n_folds=16, shuffle=True, random_state=1234)
data.get('train', 'models')['draft_ext'] = model_train_cv_parallel(model, X, y, n_jobs=1, cv=cv)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['draft_ext'] = model.predict_proba(X_test)[:, 1] - 0.5
def data_v5(data):
def get_y():
return data.get('train', 'y')
def get_X(dset='train'):
return data.extract(dset, [
('nums', None),
('cats', None),
('nans', None),
]).fillna(-999)
# 0.46394
model = LogisticXGB(n_estimators=350, learning_rate=0.05, max_depth=7, seed=42)
X, y = get_X(), get_y()
X_test = get_X('test')
cv = skl.cross_validation.StratifiedKFold(y, n_folds=16, shuffle=True, random_state=1234)
data.dset('train')['models'] = pd.DataFrame(index=X.index)
data.get('train', 'models')['draft_xgb'] = model_train_cv_parallel(model, X, y, n_jobs=1, cv=cv)['predict'] - 0.5
model.fit(X, y)
data.dset('test')['models'] = pd.DataFrame(index=X_test.index)
data.get('test', 'models')['draft_xgb'] = model.predict_proba(X_test)[:, 1] - 0.5
def data_v30(data):
scaler = skl.preprocessing.StandardScaler()
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
X = data.extract(dset, [
('match', ['lobby_type_practice']),
('models', ['time_xgb']),
('synergy_sum', None),
('item_counts', None),
('ability_counts', None),
('team_diffs', ['first_ward']),
('fb', ['first_blood_team']),
('gold_counts', None),
('xp_counts', None),
('lh_counts', None),
('kills_counts', None),
]).to_sparse(0)
scale = ['time_xgb', 'anti_synergy', 'synergy']
X[scale] = scaler.fit_transform(
X[scale]) if dset == 'train' else scaler.transform(X[scale])
return X
model = skl.linear_model.LogisticRegression(random_state=1234, C=0.005)
X, y = get_X(), get_y()
data.get('train', 'models')['common_linear'] = model_train_cv_parallel(
model, X, y, n_jobs=1)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['common_linear'] = model.predict_proba(
get_X('test'))[:, 1] - 0.5
def data_v24(data):
scaler = skl.preprocessing.StandardScaler()
def get_y():
return data.get('train', df='y')
def get_X(dset='train'):
return data.extract(dset, [
('models', ['time_xgb']), ('synergy_sum', None),
('hero_roles_bag', None),
('match',
['lobby_type_practice', 'lobby_type_public', 'lobby_type_ranked'])
],
scaler=scaler)
model = skl.linear_model.LogisticRegression(random_state=123, C=0.001)
X, y = get_X(), get_y()
data.get('train', 'models')['pre_match_linear'] = model_train_cv_parallel(
model, X, y)['predict'] - 0.5
model.fit(X, y)
data.get('test', 'models')['pre_match_linear'] = model.predict_proba(
get_X('test'))[:, 1] - 0.5