def get_feat_imp(train,ID='id',target='price_doc'):
predictors = [x for x in train.columns if x not in [ID,target]]
model = XGBRegressor( max_depth=5, learning_rate=0.05, n_estimators=385,
silent=True, objective='reg:linear', nthread=-1, min_child_weight=1,
max_delta_step=0, subsample=0.93, seed=27)
model.fit(train[predictors],train[target])
feat_imp = pd.Series(model.booster().get_fscore(),index=predictors).sort_values(ascending=False)
return feat_imp
gpfinal.drop('units_y', axis=1, inplace=True)
gpfinal.drop('releaseDate', axis=1, inplace=True)
test.drop('releaseDate', axis=1, inplace=True)
print test[test.isnull().any(axis=1)]
clf.fit(gpfinal,
final_target,
eval_metric='mae',
eval_set=[(gpfinal, final_target)])
preds = clf.predict(test)
print clf.booster().get_score()
clf2 = RandomForestClassifier(n_jobs=2, random_state=0)
clf2.fit(gpfinal, final_target)
preds2 = clf2.predict(test)
#from sklearn.model_selection import train_test_split
#X_train, X_validation, y_train, y_validation = train_test_split(gpfinal, final_target, train_size=0.7, random_state=seed)
#categorical_features_indices = np.where(gpfinal.dtypes != np.float)[0]
#from catboost import CatBoostRegressor
#model=CatBoostRegressor(iterations=100, depth=3, learning_rate=0.1, loss_function='RMSE')
#model.fit(X_train, y_train,cat_features=categorical_features_indices,eval_set=(X_validation, y_validation),plot=True)
#
#preds3 = model.predict(test)
#preds = (np.array(preds) + np.array(preds2) + np.array(preds3)) / 3
#preds = (np.array(preds) + np.array(preds2)) / 2
class Xgb:
def __init__(self, df, target_column='', id_column='', target_type='binary', categorical_columns=[], drop_columns=[], numeric_columns=[], num_training_rounds=500, verbose=1, early_stopping_rounds=None):
"""
input params:
- df (DataFrame): dataframe of training data
- target_column (string): name of target column
- id_column (string): name of id column
- target_type (string): 'linear' or 'binary'
- categorical_columns (list): list of column names of categorical data. Will perform one-hot encoding
- drop_columns (list): list of columns to drop
- numeric_columns (list): list of columns to convert to numeric
- verbose (bool): verbosity of printouts
"""
if type(df) == pd.core.frame.DataFrame:
self.df = df
self.early_stopping_rounds = early_stopping_rounds
if target_column:
self.target_column = target_column
self.id_column = id_column
self.target_type = target_type
self.categorical_columns = categorical_columns
self.numeric_columns = numeric_columns
self.drop_columns = drop_columns
self.verbose = verbose
self.num_training_rounds = num_training_rounds
# init the classifier
if self.target_type == 'binary':
self.scoring = 'auc'
self.clf = XGBClassifier(
learning_rate =0.1,
n_estimators = num_training_rounds,
subsample = 0.8,
colsample_bytree = 0.8,
objective = 'binary:logistic',
scale_pos_weight = 1,
seed = 123)
elif self.target_type == 'linear':
self.scoring = 'rmse'
self.clf = XGBRegressor(
n_estimators = num_training_rounds,
objective = 'reg:linear'
)
else:
print('please provide target column name')
else:
print('please provide pandas dataframe')
def train(self):
print('#### preprocessing ####')
self.df = self.preprocess(self.df)
print('#### training ####')
self.predictors = [x for x in self.df.columns if x not in [self.target_column, self.id_column]]
xgb_param = self.clf.get_xgb_params()
xgtrain = xgb.DMatrix(self.df[self.predictors], label=self.df[self.target_column], missing=np.nan)
try:
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds, show_progress=self.verbose)
except:
try:
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds, verbose_eval=self.verbose)
except:
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds)
self.clf.set_params(n_estimators=cvresult.shape[0])
self.clf.fit(self.df[self.predictors], self.df[self.target_column],eval_metric=self.scoring)
#Predict training set:
train_df_predictions = self.clf.predict(self.df[self.predictors])
if self.target_type == 'binary':
train_df_predprob = self.clf.predict_proba(self.df[self.predictors])[:,1]
print("Accuracy : %.4g" % metrics.accuracy_score(self.df[self.target_column].values, train_df_predictions))
print("AUC Score (Train): %f" % metrics.roc_auc_score(self.df[self.target_column], train_df_predprob))
elif self.target_type == 'linear':
print("Mean squared error: %f" % metrics.mean_squared_error(self.df[self.target_column].values, train_df_predictions))
print("Root mean squared error: %f" % np.sqrt(metrics.mean_squared_error(self.df[self.target_column].values, train_df_predictions)))
def predict(self, test_df):
print('### predicting ###')
print('## preprocessing test set')
if self.id_column in test_df:
ids = test_df[self.id_column]
if self.target_column in test_df.columns:
targets = test_df[self.target_column]
self.test_df = self.preprocess(test_df, train=False)
if self.id_column in test_df:
self.test_df[self.id_column] = ids
if self.target_column in test_df.columns:
self.test_df[self.target_column] = targets
for col in self.predictors:
if col not in self.test_df.columns:
self.test_df[col] = np.nan
if self.target_type == 'binary':
self.output = self.clf.predict_proba(self.test_df[self.predictors])[:,1]
elif self.target_type == 'linear':
self.output = self.clf.predict(self.test_df[self.predictors])
return self.output
def feature_importance(self, num_print=10, display=True):
feature_importance = sorted(list(self.clf.booster().get_fscore().items()), key = operator.itemgetter(1), reverse=True)
impt = pd.DataFrame(feature_importance)
impt.columns = ['feature', 'importance']
print(impt[:num_print])
if display:
impt[:num_print].plot("feature", "importance", kind="barh", color=sns.color_palette("deep", 3))
def preprocess(self, df, train=True):
# one hot encoding of categorical variables
print('## one hot encoding of categorical variables')
for col in self.categorical_columns:
if self.verbose:
print('one hot encoding: ', col)
df = pd.concat([df, pd.get_dummies(df[col]).rename(columns=lambda x: col+'_'+str(x))], axis=1)
df = df.drop([col], axis=1)
# if training, determine columns to be removed
if train:
# drop columns that are too sparse to be informative
self.cols_to_remove = []
print('## dropping columns below sparsity threshold')
for col in df.columns:
nan_cnt = 0
for x in df[col]:
try:
if np.isnan(x):
nan_cnt += 1
except:
pass
if nan_cnt/float(len(df[col])) > 0.6: # arbitrary cutoff, if more than 60% missing then drop
if self.verbose:
print('will drop', col)
self.cols_to_remove.append(col)
# drop columns that have no standard deviation (not informative)
print('## dropping columns with no variation')
for col in df.columns:
if df[col].dtype == 'int64' or df[col].dtype == 'float64':
if df[col].std() == 0:
print('will drop', col)
self.cols_to_remove.append(col)
if self.verbose and self.cols_to_remove:
print('dropping the following columns:', self.cols_to_remove)
df = df.drop(self.cols_to_remove, axis=1)
if self.verbose:
print('## DataFrame shape is now:', df.shape)
# convert to numerical where possible
#print('## converting numerical data to numeric dtype')
#df = df.convert_objects(convert_numeric=True)
# convert columns specified to be int and float
for col in self.numeric_columns:
if col not in self.cols_to_remove:
if self.verbose:
print('converting', col)
df[col] = pd.to_numeric(df[col], errors='coerce')
if self.verbose:
print(df[col].dtype)
# drop those marked for dropping
df = df.drop(self.drop_columns, axis=1)
# drop all those that are object type
print('## dropping non-numerical columns')
for col in df.columns:
if df[col].dtype == 'int64' or df[col].dtype == 'float64' or df[col].dtype == 'bool':
pass
else:
if self.verbose:
print('dropping because not int, float, or bool:', col)
df = df.drop([col], axis=1)
return df
def _to_int(self, num):
try:
return int(num)
except:
return
def _to_float(self, num):
try:
return float(num)
except:
return
def write_csv(self, filename, include_actual=False):
"""
write results to csv
- include actual: if actual values are known for test set, and we want to print them
"""
with open(filename, 'wb') as csvfile:
writer = csv.writer(csvfile)
headers = [self.id_column, self.target_column]
if include_actual:
headers.append('actual')
writer.writerow(headers)
for idx, value in enumerate(self.output):
test_id = self.test_df[self.id_column][idx]
test_output = self.output[idx]
to_write = [test_id, test_output]
if include_actual:
to_write.append(self.test_df[self.target_column][idx])
writer.writerow(to_write)
def save(self, filename='xgb.pkl'):
joblib.dump(self, filename)
@sym_predict.register(XGBRegressor)
def sym_predict_xgb_regressor(estimator):
dump = estimator.get_booster().get_dump()
inputs = tuple(map(RealVariable, estimator.get_booster().feature_names))
Var = VariableFactory(existing=inputs)
calls = tuple(
map(
lambda x: ((Var(), ), (x, inputs)),
map(lambda x: Function(inputs, tuple(), (x.expression(), )),
map(Node.from_str, dump))))
output = reduce(__add__, map(compose(first, first), calls)) + RealNumber(
0.5) # TODO: Why do I have to add 0.5?
return Function(inputs, calls, (output, ))
if __name__ == '__main__':
model = XGBRegressor(n_estimators=2, max_depth=1)
X, y = make_regression()
X = DataFrame(X, columns=['x%d' % i for i in range(X.shape[1])])
model.fit(X, y)
print(sym_predict(model))
code = sklearn2code(model, ['predict'], numpy_flat)
print(code)
print(model.booster().get_dump()[0])
module = exec_module('module', code)
print(module.predict(**X.loc[:10, :]))
print(model.predict(X.loc[:10, :]))
1 + 1
class Xgb:
def __init__(self,
df,
target_column='',
id_column='',
target_type='binary',
categorical_columns=[],
drop_columns=[],
numeric_columns=[],
num_training_rounds=500,
verbose=1,
sample_fraction=1.0,
n_samples=1,
early_stopping_rounds=None,
prefix='xgb_model',
scoring=None):
"""
input params:
- df (DataFrame): dataframe of training data
- target_column (string): name of target column
- id_column (string): name of id column
- target_type (string): 'linear' or 'binary'
- categorical_columns (list): list of column names of categorical data. Will perform one-hot encoding
- drop_columns (list): list of columns to drop
- numeric_columns (list): list of columns to convert to numeric
- verbose (bool): verbosity of printouts
"""
# checks for sampling
sample_fraction = float(sample_fraction)
if sample_fraction > 1:
sample_fraction = 1.0
if sample_fraction * n_samples > 1:
n_samples = round(1.0 / sample_fraction)
if sample_fraction <= 0:
print('sample_fraction 0 or negative, switching to 0.1')
sample_fraction = 0.1
# if sample_fraction is results in sample smaller than 1
if round(sample_fraction * len(df)) == 0:
sample_fraction = 1.0 / len(df)
# check if data is dataframe
if type(df) == pd.core.frame.DataFrame:
self.df = df
self.early_stopping_rounds = early_stopping_rounds
if target_column:
self.target_column = target_column
self.id_column = id_column
self.target_type = target_type
self.categorical_columns = categorical_columns
self.numeric_columns = numeric_columns
self.drop_columns = drop_columns
self.verbose = verbose
self.sample_fraction = sample_fraction
self.n_samples = n_samples
self.num_training_rounds = num_training_rounds
self.prefix = prefix
# init the classifier:
if self.target_type == 'binary':
self.scoring = 'auc'
self.clf = XGBClassifier(learning_rate=0.1,
n_estimators=num_training_rounds,
subsample=0.8,
colsample_bytree=0.8,
objective='binary:logistic',
scale_pos_weight=1,
seed=123)
elif self.target_type == 'multiclass':
self.scoring = 'merror'
self.clf = XGBClassifier(learning_rate=0.1,
n_estimators=num_training_rounds,
subsample=0.8,
colsample_bytree=0.8,
objective='multi:softmax',
scale_pos_weight=1,
seed=123)
elif self.target_type == 'linear':
self.scoring = 'rmse'
self.clf = XGBRegressor(n_estimators=num_training_rounds,
objective='reg:linear')
# if preferred scoring metric is stated:
if scoring:
self.scoring = scoring
else:
print('please provide target column name')
else:
print('please provide pandas dataframe')
def train(self):
print('#### preprocessing ####')
self.df = self.preprocess(self.df)
print('#### training ####')
self.predictors = [
x for x in self.df.columns
if x not in [self.target_column, self.id_column]
]
xgb_param = self.clf.get_xgb_params()
# if subsampling
if self.sample_fraction == 1.0:
df_list = [self.df]
else:
df_list = self.random_sample(df=self.df,
fraction=self.sample_fraction,
n_samples=self.n_samples)
print(df_list)
for idx, current_df in enumerate(df_list):
print('ITERATION ' + str(idx + 1) + ' of ' + str(self.n_samples) +
', sample_fraction=' + str(self.sample_fraction))
xgtrain = xgb.DMatrix(current_df[self.predictors],
label=current_df[self.target_column],
missing=np.nan)
try:
cvresult = xgb.cv(
xgb_param,
xgtrain,
num_boost_round=self.clf.get_params()['n_estimators'],
nfold=5,
metrics=[self.scoring],
early_stopping_rounds=self.early_stopping_rounds,
show_progress=self.verbose)
except:
try:
cvresult = xgb.cv(
xgb_param,
xgtrain,
num_boost_round=self.clf.get_params()['n_estimators'],
nfold=5,
metrics=[self.scoring],
early_stopping_rounds=self.early_stopping_rounds,
verbose_eval=self.verbose)
except:
xgb_param['num_class'] = len(
current_df[self.target_column].unique())
cvresult = xgb.cv(
xgb_param,
xgtrain,
num_boost_round=self.clf.get_params()['n_estimators'],
nfold=5,
metrics=[self.scoring],
early_stopping_rounds=self.early_stopping_rounds)
self.clf.set_params(n_estimators=cvresult.shape[0])
print('fitting model')
self.clf.fit(current_df[self.predictors],
current_df[self.target_column],
eval_metric=self.scoring)
#Predict training set:
train_df_predictions = self.clf.predict(
current_df[self.predictors])
if self.target_type == 'binary' or self.target_type == 'multiclass':
train_df_predprob = self.clf.predict_proba(
current_df[self.predictors])[:, 1]
print("Accuracy : %.4g" % metrics.accuracy_score(
current_df[self.target_column].values,
train_df_predictions))
if self.target_type == 'binary':
print("AUC Score (Train): %f" % metrics.roc_auc_score(
current_df[self.target_column], train_df_predprob))
elif self.target_type == 'linear':
print("Mean squared error: %f" % metrics.mean_squared_error(
current_df[self.target_column].values,
train_df_predictions))
print("Root mean squared error: %f" % np.sqrt(
metrics.mean_squared_error(
current_df[self.target_column].values,
train_df_predictions)))
filename = self.prefix + '_' + str(idx) + '.pkl'
self.save(filename)
def predict(self,
test_df,
return_multi_outputs=False,
return_mean_std=False):
print('### predicting ###')
print('## preprocessing test set')
if self.id_column in test_df:
ids = test_df[self.id_column]
if self.target_column in test_df.columns:
targets = test_df[self.target_column]
self.test_df = self.preprocess(test_df, train=False)
if self.id_column in test_df:
self.test_df[self.id_column] = ids
if self.target_column in test_df.columns:
self.test_df[self.target_column] = targets
for col in self.predictors:
if col not in self.test_df.columns:
self.test_df[col] = np.nan
# prediction
print('## predicting from test set')
output_list = []
output = None
for idx, ns in enumerate(range(self.n_samples)):
if self.n_samples == 1:
if self.target_type == 'binary':
output = self.clf.predict_proba(
self.test_df[self.predictors])[:, 1]
elif self.target_type == 'linear':
output = self.clf.predict(self.test_df[self.predictors])
else:
try:
filename = self.prefix + '_' + str(idx) + '.pkl'
xgb_load = self.load(filename)
if self.target_type == 'binary':
output = xgb_load.clf.predict_proba(
self.test_df[self.predictors])[:, 1]
elif self.target_type == 'linear':
output = xgb_load.clf.predict(
self.test_df[self.predictors])
output_list.append(list(output))
except IOError:
print('no file found, skipping')
# average the outputs if n_samples is more than one
if self.n_samples == 1:
self.output = output
try:
self.multi_outputs = [list(output)]
except:
self.multi_outputs = None
else:
self.output = np.mean(output_list, axis=0)
self.multi_outputs = output_list
if return_multi_outputs:
return self.multi_outputs
elif return_mean_std:
return (self.output, np.std(output_list, axis=0))
else:
return self.output
def feature_importance(self, num_print=10, display=True):
feature_importance = sorted(list(
self.clf.booster().get_fscore().items()),
key=operator.itemgetter(1),
reverse=True)
impt = pd.DataFrame(feature_importance)
impt.columns = ['feature', 'importance']
print(impt[:num_print])
if display:
impt[:num_print].plot("feature",
"importance",
kind="barh",
color=sns.color_palette("deep", 3))
def preprocess(self, df, train=True):
# one hot encoding of categorical variables
print('## one hot encoding of categorical variables')
for col in self.categorical_columns:
if self.verbose:
print('one hot encoding: ', col)
df = pd.concat([
df,
pd.get_dummies(
df[col]).rename(columns=lambda x: col + '_' + str(x))
],
axis=1)
df = df.drop([col], axis=1)
# if training, determine columns to be removed
if train:
# drop columns that are too sparse to be informative
self.cols_to_remove = []
print('## dropping columns below sparsity threshold')
for col in df.columns:
nan_cnt = 0
for x in df[col]:
try:
if np.isnan(x):
nan_cnt += 1
except:
pass
if nan_cnt / float(
len(df[col])
) > 0.6: # arbitrary cutoff, if more than 60% missing then drop
if self.verbose:
print('will drop', col)
self.cols_to_remove.append(col)
# drop columns that have no standard deviation (not informative)
print('## dropping columns with no variation')
for col in df.columns:
if col is not self.target_column:
if df[col].dtype == 'int64' or df[col].dtype == 'float64':
if df[col].std() == 0:
print('will drop', col)
self.cols_to_remove.append(col)
if self.verbose and self.cols_to_remove:
print('dropping the following columns:', self.cols_to_remove)
df = df.drop(self.cols_to_remove, axis=1)
if self.verbose:
print('## DataFrame shape is now:', df.shape)
# convert to numerical where possible
#print('## converting numerical data to numeric dtype')
#df = df.convert_objects(convert_numeric=True)
# convert columns specified to be int and float
for col in self.numeric_columns:
if self.verbose:
print('converting', col)
df[col] = pd.to_numeric(df[col], errors='coerce')
if self.verbose:
print(df[col].dtype)
df = df.drop(self.drop_columns, axis=1)
# drop all those that are object type
print('## dropping non-numerical columns')
for col in df.columns:
if df[col].dtype == 'int64' or df[col].dtype == 'float64' or df[
col].dtype == 'bool':
pass
else:
if self.verbose:
print('dropping because not int, float, or bool:', col)
df = df.drop([col], axis=1)
return df
def _to_int(self, num):
try:
return int(num)
except:
return
def _to_float(self, num):
try:
return float(num)
except:
return
def random_sample(self, df, fraction=0.2, n_samples=None):
"""
splits into random samples
- n_samples: how many samples you want returned (default = All)
- fraction : what fraction of data to include in the sample (default = 0.2)
"""
print('constructing random samples')
num_rows = len(df)
len_sample = round(fraction * num_rows)
# create list of slice index lists
indices = list(range(0, num_rows))
print('INDICES', indices)
slice_list = []
tmp_idx_list = []
while len(indices) > 0:
while len(tmp_idx_list) < len_sample and len(indices) > 0:
idx = indices.pop(random.randrange(len(indices)))
tmp_idx_list.append(idx)
slice_list.append(tmp_idx_list)
tmp_idx_list = []
# get slices
sample_list = []
for s in range(n_samples):
try:
sample_list.append(df.loc[slice_list[s], :])
except:
pass
return sample_list
def write_csv(self, filename, include_actual=False):
"""
write results to csv
- include actual: if actual values are known for test set, and we want to print them
"""
with open(filename, 'wb') as csvfile:
writer = csv.writer(csvfile)
headers = [self.id_column, self.target_column]
if include_actual:
headers.append('actual')
writer.writerow(headers)
try:
for idx, value in enumerate(self.output):
test_id = self.test_df[self.id_column][idx]
test_output = self.output[idx]
to_write = [test_id, test_output]
if include_actual:
to_write.append(self.test_df[self.target_column][idx])
writer.writerow(to_write)
print('results written to ' + filename)
except:
print('write_csv failed')
def save(self, filename='xgb.pkl'):
joblib.dump(self, filename)
def load(self, model_file='xgb.pkl'):
xgb = joblib.load(model_file)
return xgb
for sample in range(p.N_SAMPLES):
print('Sample {} size: {}'.format(sample, len(indexes[sample])))
# List containing all predictions for each sample
predictions = []
# Train each sample individually and average the predictions
for sample in range(p.N_SAMPLES):
print('\n\nTraining sample {}'.format(sample))
# Train sample from weeks 8 and 9
train_week([8, 9], indexes[sample], model)
# Test sample is the next one in the list
sample_to_test = (sample + 1) % p.N_SAMPLES
# Get best features and save them
pd.Series(model.booster().get_fscore()).sort_values(ascending=False). \
to_csv('{}/best_features_sample_{}.csv'.format(FEAT_DIR, sample))
# Test
print('\nTesting on sample {}'.format(sample_to_test))
rmsle = test_week([8, 9], indexes[sample_to_test], model)
print('\n--> RMSLE = {}'.format(rmsle))
# Get predictions, average week10 with previous ones if the list is not
# empty
print('\nGetting predictions')
week10 = []
if p.WEEK10_OLD_PRED:
# get IDs from week 10 (need to load week 10...)
data_10_ids = list(load_week(10, 1).id)
class Xgb:
def __init__(self, df, target_column='', id_column='', target_type='binary', categorical_columns=[], drop_columns=[], numeric_columns=[], num_training_rounds=500, verbose=1, sample_fraction=1.0, n_samples=1, early_stopping_rounds=None, prefix='xgb_model', scoring=None):
"""
input params:
- df (DataFrame): dataframe of training data
- target_column (string): name of target column
- id_column (string): name of id column
- target_type (string): 'linear' or 'binary'
- categorical_columns (list): list of column names of categorical data. Will perform one-hot encoding
- drop_columns (list): list of columns to drop
- numeric_columns (list): list of columns to convert to numeric
- verbose (bool): verbosity of printouts
"""
# checks for sampling
sample_fraction = float(sample_fraction)
if sample_fraction > 1:
sample_fraction = 1.0
if sample_fraction * n_samples > 1:
n_samples = round(1.0/sample_fraction)
if sample_fraction <= 0:
print('sample_fraction 0 or negative, switching to 0.1')
sample_fraction = 0.1
# if sample_fraction is results in sample smaller than 1
if round(sample_fraction * len(df)) == 0:
sample_fraction = 1.0/len(df)
# check if data is dataframe
if type(df) == pd.core.frame.DataFrame:
self.df = df
self.early_stopping_rounds = early_stopping_rounds
if target_column:
self.target_column = target_column
self.id_column = id_column
self.target_type = target_type
self.categorical_columns = categorical_columns
self.numeric_columns = numeric_columns
self.drop_columns = drop_columns
self.verbose = verbose
self.sample_fraction = sample_fraction
self.n_samples = n_samples
self.num_training_rounds = num_training_rounds
self.prefix = prefix
# init the classifier:
if self.target_type == 'binary':
self.scoring = 'auc'
self.clf = XGBClassifier(
learning_rate =0.1,
n_estimators = num_training_rounds,
subsample = 0.8,
colsample_bytree = 0.8,
objective = 'binary:logistic',
scale_pos_weight = 1,
seed = 123)
elif self.target_type == 'multiclass':
self.scoring = 'merror'
self.clf = XGBClassifier(
learning_rate =0.1,
n_estimators = num_training_rounds,
subsample = 0.8,
colsample_bytree = 0.8,
objective = 'multi:softmax',
scale_pos_weight = 1,
seed = 123)
elif self.target_type == 'linear':
self.scoring = 'rmse'
self.clf = XGBRegressor(
n_estimators = num_training_rounds,
objective = 'reg:linear'
)
# if preferred scoring metric is stated:
if scoring:
self.scoring = scoring
else:
print('please provide target column name')
else:
print('please provide pandas dataframe')
def train(self):
print('#### preprocessing ####')
self.df = self.preprocess(self.df)
print('#### training ####')
self.predictors = [x for x in self.df.columns if x not in [self.target_column, self.id_column]]
xgb_param = self.clf.get_xgb_params()
# if subsampling
if self.sample_fraction == 1.0:
df_list = [self.df]
else:
df_list = self.random_sample(df=self.df, fraction=self.sample_fraction, n_samples=self.n_samples)
print(df_list)
for idx, current_df in enumerate(df_list):
print('ITERATION ' + str(idx) + ' of ' + str(self.n_samples) +', sample_fraction=' + str(self.sample_fraction))
xgtrain = xgb.DMatrix(current_df[self.predictors], label=current_df[self.target_column], missing=np.nan)
try:
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds, show_progress=self.verbose)
except:
try:
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds, verbose_eval=self.verbose)
except:
xgb_param['num_class'] = len(current_df[self.target_column].unique())
cvresult = xgb.cv(xgb_param, xgtrain, num_boost_round=self.clf.get_params()['n_estimators'], nfold=5,
metrics=[self.scoring], early_stopping_rounds=self.early_stopping_rounds)
self.clf.set_params(n_estimators=cvresult.shape[0])
self.clf.fit(current_df[self.predictors], current_df[self.target_column], eval_metric=self.scoring)
#Predict training set:
train_df_predictions = self.clf.predict(current_df[self.predictors])
if self.target_type == 'binary' or self.target_type == 'multiclass':
train_df_predprob = self.clf.predict_proba(current_df[self.predictors])[:,1]
print("Accuracy : %.4g" % metrics.accuracy_score(current_df[self.target_column].values, train_df_predictions))
if self.target_type == 'binary':
print("AUC Score (Train): %f" % metrics.roc_auc_score(current_df[self.target_column], train_df_predprob))
elif self.target_type == 'linear':
print("Mean squared error: %f" % metrics.mean_squared_error(current_df[self.target_column].values, train_df_predictions))
print("Root mean squared error: %f" % np.sqrt(metrics.mean_squared_error(current_df[self.target_column].values, train_df_predictions)))
filename = self.prefix + '_' + str(idx) + '.pkl'
self.save(filename)
def predict(self, test_df, return_multi_outputs=False, return_mean_std=False):
print('### predicting ###')
print('## preprocessing test set')
if self.id_column in test_df:
ids = test_df[self.id_column]
if self.target_column in test_df.columns:
targets = test_df[self.target_column]
self.test_df = self.preprocess(test_df, train=False)
if self.id_column in test_df:
self.test_df[self.id_column] = ids
if self.target_column in test_df.columns:
self.test_df[self.target_column] = targets
for col in self.predictors:
if col not in self.test_df.columns:
self.test_df[col] = np.nan
# prediction
print('## predicting from test set')
output_list = []
output = None
for idx, ns in enumerate(range(self.n_samples)):
if self.n_samples == 1:
xgb = self
if self.target_type == 'binary':
output = xgb.clf.predict_proba(self.test_df[self.predictors])[:,1]
elif self.target_type == 'linear':
output = xgb.clf.predict(self.test_df[self.predictors])
else:
try:
filename = self.prefix + '_' + str(idx) + '.pkl'
xgb = self.load(filename)
if self.target_type == 'binary':
output = xgb.clf.predict_proba(self.test_df[self.predictors])[:,1]
elif self.target_type == 'linear':
output = xgb.clf.predict(self.test_df[self.predictors])
output_list.append(list(output))
except IOError:
print('no file found, skipping')
# average the outputs if n_samples is more than one
if self.n_samples == 1:
self.output = output
try:
self.multi_outputs = [list(output)]
except:
self.multi_outputs = None
else:
self.output = np.mean(output_list, axis=0)
self.multi_outputs = output_list
if return_multi_outputs:
return self.multi_outputs
elif return_mean_std:
return (self.output, np.std(output_list, axis=0))
else:
return self.output
def feature_importance(self, num_print=10, display=True):
feature_importance = sorted(list(self.clf.booster().get_fscore().items()), key = operator.itemgetter(1), reverse=True)
impt = pd.DataFrame(feature_importance)
impt.columns = ['feature', 'importance']
print(impt[:num_print])
if display:
impt[:num_print].plot("feature", "importance", kind="barh", color=sns.color_palette("deep", 3))
def preprocess(self, df, train=True):
# one hot encoding of categorical variables
print('## one hot encoding of categorical variables')
for col in self.categorical_columns:
if self.verbose:
print('one hot encoding: ', col)
df = pd.concat([df, pd.get_dummies(df[col]).rename(columns=lambda x: col+'_'+str(x))], axis=1)
df = df.drop([col], axis=1)
# if training, determine columns to be removed
if train:
# drop columns that are too sparse to be informative
self.cols_to_remove = []
print('## dropping columns below sparsity threshold')
for col in df.columns:
nan_cnt = 0
for x in df[col]:
try:
if np.isnan(x):
nan_cnt += 1
except:
pass
if nan_cnt/float(len(df[col])) > 0.6: # arbitrary cutoff, if more than 60% missing then drop
if self.verbose:
print('will drop', col)
self.cols_to_remove.append(col)
# drop columns that have no standard deviation (not informative)
print('## dropping columns with no variation')
for col in df.columns:
if df[col].dtype == 'int64' or df[col].dtype == 'float64':
if df[col].std() == 0:
print('will drop', col)
self.cols_to_remove.append(col)
if self.verbose and self.cols_to_remove:
print('dropping the following columns:', self.cols_to_remove)
df = df.drop(self.cols_to_remove, axis=1)
if self.verbose:
print('## DataFrame shape is now:', df.shape)
# convert to numerical where possible
#print('## converting numerical data to numeric dtype')
#df = df.convert_objects(convert_numeric=True)
# convert columns specified to be int and float
for col in self.numeric_columns:
if self.verbose:
print('converting', col)
df[col] = pd.to_numeric(df[col], errors='coerce')
if self.verbose:
print(df[col].dtype)
df = df.drop(self.drop_columns, axis=1)
# drop all those that are object type
print('## dropping non-numerical columns')
for col in df.columns:
if df[col].dtype == 'int64' or df[col].dtype == 'float64' or df[col].dtype == 'bool':
pass
else:
if self.verbose:
print('dropping because not int, float, or bool:', col)
df = df.drop([col], axis=1)
return df
def _to_int(self, num):
try:
return int(num)
except:
return
def _to_float(self, num):
try:
return float(num)
except:
return
def random_sample(self, df, fraction=0.2, n_samples=None):
"""
splits into random samples
- n_samples: how many samples you want returned (default = All)
- fraction : what fraction of data to include in the sample (default = 0.2)
"""
print('constructing random samples')
num_rows = len(df)
len_sample = round(fraction * num_rows)
# create list of slice index lists
indices = range(0,num_rows)
slice_list = []
tmp_idx_list = []
while len(indices) > 0:
while len(tmp_idx_list) < len_sample and len(indices) > 0:
idx = indices.pop(random.randrange(len(indices)))
tmp_idx_list.append(idx)
slice_list.append(tmp_idx_list)
tmp_idx_list = []
# get slices
sample_list = []
for s in range(n_samples):
try:
sample_list.append(df.loc[slice_list[s],:])
except:
pass
return sample_list
def write_csv(self, filename, include_actual=False):
"""
write results to csv
- include actual: if actual values are known for test set, and we want to print them
"""
with open(filename, 'wb') as csvfile:
writer = csv.writer(csvfile)
headers = [self.id_column, self.target_column]
if include_actual:
headers.append('actual')
writer.writerow(headers)
try:
for idx, value in enumerate(self.output):
test_id = self.test_df[self.id_column][idx]
test_output = self.output[idx]
to_write = [test_id, test_output]
if include_actual:
to_write.append(self.test_df[self.target_column][idx])
writer.writerow(to_write)
print('results written to ' + filename)
except:
print('write_csv failed')
def save(self, filename='xgb.pkl'):
joblib.dump(self, filename)
def load(self, model_file='xgb.pkl'):
xgb = joblib.load(model_file)
return xgb
def XGB_Main(train, test):
print "XGB_Main"
train_y = train["trip_duration"].values
train_y = np.log(train_y + 1)
print "features:", x_columns
print "feature size:", len(x_columns)
train_x = train[x_columns].values
test_x = test[x_columns].values
start = time.time()
Xtr, Xv, ytr, yv = train_test_split(train_x,
train_y,
test_size=0.3,
random_state=2017)
dtrain = xgb.DMatrix(Xtr, label=ytr)
dvalid = xgb.DMatrix(Xv, label=yv)
dtest = xgb.DMatrix(test_x)
watchlist = [(dtrain, 'train'), (dvalid, 'valid')]
# Try different parameters! My favorite is random search :)
lr = 0.05
n_rounds = 5000
early_stopping_rounds = 50
xgb_pars = {
'min_child_weight': 100,
'eta': lr,
'colsample_bytree': 0.5,
'max_depth': 10,
'subsample': 0.85,
'lambda': 0,
'alpha': 0,
'gamma': 0,
'nthread': -1,
'booster': 'gbtree',
'silent': 1,
'eval_metric': 'rmse',
'objective': 'reg:linear'
}
# You could try to train with more epoch
# model = xgb.train(xgb_pars, dtrain, n_rounds, watchlist, early_stopping_rounds=early_stopping_rounds,
# maximize=False, verbose_eval=1)
model = XGBRegressor(
learning_rate=lr,
n_estimators=n_rounds,
max_depth=xgb_pars["max_depth"],
min_child_weight=xgb_pars["min_child_weight"],
gamma=xgb_pars["gamma"], # 指定分裂节点损失下降的最小值
subsample=xgb_pars["subsample"],
colsample_bytree=xgb_pars["colsample_bytree"],
objective=xgb_pars["objective"],
nthread=xgb_pars["nthread"],
reg_lambda=xgb_pars["lambda"], # l2正则
reg_alpha=xgb_pars["alpha"], # l1正则
seed=2017)
model.fit(Xtr,
ytr,
early_stopping_rounds=early_stopping_rounds,
eval_metric=xgb_pars["eval_metric"],
eval_set=[[Xv, yv]])
print("Time taken by above cell is {}.".format(time.time() - start))
print('Modeling RMSLE %.5f' % model.best_score)
# exit(1)
# xgb.cv(xgb_pars, dtrain, num_boost_round=n_rounds)
# grid seach sv
# param_test1 = {
# 'max_depth': np.arange(4, 22, 2),+
# 'min_child_weight': np.arange(40, 100, 5)
# }
# train_model(model, train_x, train_y, cv=3, grid_search=True, re_fit=False, grid_params=param_test1)
predicts = model.predict(test_x, ntree_limit=model.best_ntree_limit)
predicts = np.exp(predicts) - 1
test["trip_duration"] = predicts
csv__format = "XGB_{}rounds_{}lr_{}f_{}weight_" \
"{}depth_{}cb_{}subsample_{}gamma_{}lambda_{}alpha.csv".format(n_rounds, lr, len(x_columns),
xgb_pars["min_child_weight"],
xgb_pars["max_depth"],
xgb_pars["colsample_bytree"],
xgb_pars["subsample"],
xgb_pars["gamma"], xgb_pars["lambda"],
xgb_pars["alpha"])
save_path = "../result/" + csv__format
save_result(test[["id", "trip_duration"]], save_path)
# save model
model_save_path = "../result/MODEL/" + csv__format
model.booster().save_model(model_save_path.replace("csv", "model"))
# feature importance
feature_importance_dict = model.booster().get_fscore()
print feature_importance_dict
