def build_prediction_model(path, percentage, para_tuning_mark, last_mark):
# Read data
if not last_mark:
train = pandas.read_csv(path + "train_" + str(percentage))
dev = pandas.read_csv(path + "dev_" + str(percentage))
test = pandas.read_csv(path + "test_" + str(percentage))
else:
if percentage == 1.0:
return
train = pandas.read_csv(path + "train_" + str(percentage) + "_last")
dev = pandas.read_csv(path + "dev_" + str(percentage) + "_last")
test = pandas.read_csv(path + "test_" + str(percentage) + "_last")
# Check whether there are any columns with all zeros
nonzero_colums = train.loc[:, (train != 0).any(axis=0)].columns
# Scale
scale_pos_weight = {0: 0, 1: 0}
for index, value in train['label'].iteritems():
scale_pos_weight[value] += 1
scale_value = scale_pos_weight[0] / float(scale_pos_weight[1])
# Build prediction model
predictors = [x for x in nonzero_colums if x not in ['label']]
if para_tuning_mark:
# Parameter turning guide:
# https://www.analyticsvidhya.com/blog/2016/02/complete-guide-parameter-tuning-gradient-boosting-gbm-python/
# https://www.analyticsvidhya.com/blog/2016/03/complete-guide-parameter-tuning-xgboost-with-codes-python/
# Parameter: learning_rate
para_tuning_0(train, dev, test, scale_value)
# para_tuning_1(train, dev, test, scale_value)
# para_tuning_2(train, dev, test, scale_value)
# para_tuning_3(train, dev, test, scale_value)
# para_tuning_4(train, dev, test, scale_value)
else:
xgb = XGBClassifier(learning_rate=0.015,
n_estimators=686,
max_depth=9,
min_child_weight=5,
gamma=0.0,
subsample=0.8,
colsample_bytree=0.8,
reg_alpha=0.01,
objective='binary:logistic',
nthread=4,
scale_pos_weight=scale_value,
seed=27)
xgb.fit(train[predictors], train['label'], eval_metric='auc')
dtest_predprob = xgb.predict_proba(test[predictors])[:, 1]
print(
"AUC/F1 Score/Kappa (Test):\t%f\t%f\t%f\t" %
(metrics.roc_auc_score(test['label'], dtest_predprob),
metrics.f1_score(test['label'], dtest_predprob.round()),
metrics.cohen_kappa_score(test['label'], dtest_predprob.round())))
def train(X_train, X_test, y_train, y_test):
xgb = XGBClassifier(
learning_rate=0.1,
n_estimators=20,
max_depth=4,
min_child_weight=1,
gamma=1,
subsample=0.6,
colsample_bytree=0.6,
objective='binary:logistic',
scale_pos_weight=1,
nthread=4,
max_delta_step=10,
#scale_pos_weight=1,
seed=27,
cv=3,
reg_alpha=0.01,
eval_metric="error")
print(X_train.shape)
#print("修改前")
# print(y_train.shape[1])
# xgb1.set_params(params)
xgb.fit(X_train, y_train)
model_metrics(xgb, X_train, X_test, y_train, y_test)
return xgb
def prediction():
xgb = xgboost.XGBRegressor(n_estimators=100, learning_rate=0.08, gamma=0, subsample=0.75,
colsample_bytree=1, max_depth=7)
traindf, testdf = train_test_split(X_train, test_size = 0.3)
xgb.fit(X_train,y_train)
predictions = xgb.predict(X_test)
print(explained_variance_score(predictions,y_test))
def XGBoost_classifier(X_train, train_target, X_test):
X_test = X_test.values
xgb = XGBClassifier()
xgb.fit(X_train, train_target)
hyp = xgb.predict(X_test)
return hyp
def xgboost(train_x,train_y,test_x,test_y):
import xgboost as xgb
xgb = xgb.XGBClassifier(n_estimators=150,min_samples_leaf=3,max_depth=6)
xgb.fit(train_x,train_y)
y_pred = xgb.predict(test_x)
print(classification_report(test_y,y_pred))
print(confusion_matrix(test_y,y_pred))
print('gbdt accuracy is', accuracy_score(test_y,y_pred))
def train(ite):
print(i)
data = train_target_0.sample(700) #数据显示1 ：0 = 17：2（》0.5）
data = data.append(train_target_1)
y_ = data.target
del data['target']
xgb.fit(data, y_)
# train_p[ite] = xgb.predict(train_data)
res[ite] = xgb.predict_proba(test_data)[:, 1]
def XGBscore(self):
X_train_leaves = self.x_train
y_train = self.y_train
X_test_leaves = self.x_test
y_test = self.y_test
xgb = XGBClassifier()
xgb.fit(X_train_leaves, y_train)
Y_pred_xgb = xgb.predict(X_test_leaves)
xgb_auc = roc_auc_score(y_test, Y_pred_xgb)
print('GBDT + XGB auc: %.5f' % xgb_auc)
def test_xgboost_sklearn_gressor():
l1 = []
from sklearn.datasets import load_boston
boston = load_boston()
xgb = XGBRegressor()
xgb.fit(boston.data, boston.target)
predictions = xgb.predict(boston.data)
l1 += predictions.tolist()
print(predictions)
print(type(predictions))
def train_xgb(data):
X = data.drop(['cause'], axis=1).values
Y = data['cause'].values
X_train, X_test, y_train, y_test = train_test_split(X,
Y,
test_size=0.2,
random_state=0)
xgb = XGBClassifier(n_estimators=300)
xgb.fit(X_train, y_train)
preds = xgb.predict(X_test)
acc_xgb = (preds == y_test).sum().astype(float) / len(preds) * 100
print("XGBoost's prediction accuracy is: %3.2f" % (acc_xgb))
def check_performance(g_z,
train_data,
test_data,
data_cols,
label_cols=[],
seed=0,
with_class=False,
data_dim=2):
#train_data,test_data = load_preprocess_aps_data()
if len(label_cols) > 0:
gen_df = pd.DataFrame(g_z[:, :-1], columns=data_cols)
else:
gen_df = pd.DataFrame(g_z, columns=data_cols)
gen_df['failure'] = np.ones((g_z.shape[0], 1))
combined_train_df = pd.concat([train_data, gen_df])
print(train_data.shape, gen_df.shape, combined_train_df.shape)
xgb_params = {
# 'tree_method': 'hist', # for faster evaluation
'max_depth': 3, # for faster evaluation
'n_estimators': 18,
#'objective': 'binary:logistic',
'random_state': 0,
#'eval_metric': 'auc', # allows for balanced or unbalanced classes
'scale_pos_weight': 40,
'min_child_weight': 44,
'silent': 1
}
X_train = combined_train_df[combined_train_df.columns.drop(
'failure')].values
y_train = combined_train_df.failure
X_test = test_data[test_data.columns.drop('failure')].values
y_test = test_data.failure
xgb = XGBClassifier(max_depth=3,
n_estimators=18,
n_jobs=-1,
scale_pos_weight=40,
min_child_weight=44)
xgb.fit(X_train, y_train)
y_pred = xgb.predict(X_test)
# dtrain = xgb.DMatrix(X_train, y_train, feature_names=data_cols + label_cols)
# dtest = xgb.DMatrix(X_test, feature_names=data_cols + label_cols)
# xgb_test = xgb.train(xgb_params, dtrain, num_boost_round=10) # limit to ten rounds for faster evaluation
#
# y_pred = np.round(xgb_test.predict(dtest))
print('Test performance confusion', confusion_matrix(
y_test, y_pred)) # assumes balanced real and generated datasets
return aps_cost(y_pred,
y_test) # assumes balanced real and generated datasets
def main():
## dummy test for code working till model class
preprocessing = Preprocessing(
config['weather_file_path'], config['fire_data_file_path'],
['Datetime'], [
'dt_iso', 'temp', 'pressure', 'humidity', 'wind_speed', 'wind_deg',
'rain_1h', 'rain_3h', 'snow_1h', 'snow_3h', 'clouds_all'
])
preprocessing.start_preprocessing()
data = Data(preprocessing.joined_data)
train_x, train_y, test_x, test_y = data.get_train_test()
xgb = Model((train_x, train_y, test_x, test_y))
xgb.fit()
predictions, target = xgb.make_predict()
def fonction_model_xgb(data):
df = fonction_select_xgb(data)
X = df.drop("tx_rec_marg_Bin",axis = 1)
y = df["tx_rec_marg_Bin"]
X_train, X_test,y_train, y_test = train_test_split(X,y,test_size=0.3,random_state = 0)
kf = KFold(n_splits=3)
kf.get_n_splits(X)
Quant=df[[col for col in df.columns.to_list() if df[col].nunique() > 3]]
num = list(Quant.columns)
scaler = StandardScaler().fit(X_train[num])
X_train[num] = scaler.transform(X_train[num])
X_test[num] = scaler.transform(X_test[num])
xgb = XGBClassifier(criterion = 'gini',max_depth = 7, max_features = 'auto', n_estimators = 500)
#grid_xgb = GridSearchCV (estimator = xgb, param_grid=param_grid ,scoring="accuracy")
#print(grid_rf.best_params_)
xgb.fit(X_train, y_train)
y_pred = xgb.predict(X_test)
print(classification_report(y_test,y_pred))
#print(grid_xgb.best_params_)
xgb_shap = XGBClassifier(criterion = 'gini',max_depth = 7, max_features = 'auto', n_estimators = 500)
xgb_shap.fit(X_train, y_train)
shap_values = shap.TreeExplainer(xgb_shap).shap_values(X_train)
print(shap.summary_plot(shap_values, X_train, plot_type="bar"))
print(confusion_matrix(y_test,y_pred))
print(f1_score(y_pred,y_test, average='micro'))
return data
def XGBoost(X_train,X_test,Y_train,Y_test):
xgb = XGBClassifier()
# Fitting the model
xgb_model = xgb.fit(X_train, Y_train)
# Predicting results
y_pred = xgb_model.predict(X_test)
#Evaluation
model_train_score = xgb_model.score(X_train,Y_train)
model_test_score = xgb_model.score(X_test,Y_test)
conf_matrix = confusion_matrix(Y_test, y_pred)
print ('XGBoost MODEL TEST SCORE: {0:.5f}'.format(model_train_score))
print ('XGBoost MODEL TEST SCORE: {0:.5f}'.format(model_test_score))
print("XGBoost ACCURACY: {0:.2f}".format(accuracy_score(Y_test, y_pred)))
print("XGBoost ROC-AUC: {0:.2f}".format(roc_auc_score(Y_test, y_pred)))
print("XGBoost PRECISION: {0:.2f}".format(precision_score(Y_test, y_pred)))
print("XGBoost RECALL: {0:.2f}".format(recall_score(Y_test, y_pred)))
print("XGBoost Confusion Matrix:\n",conf_matrix)
print ('\nXGBoost True Negatives: ', conf_matrix[0,0])
print ('XGBoost False Negatives: ', conf_matrix[1,0])
print ('XGBoost True Positives: ', conf_matrix[1,1])
print ('XGBoost False Positives: ', conf_matrix[0,1])
return xgb_model
def runXGBoost(train_data_mix_n, train_Y, test_data_mix_n, test_Y):
xgb = XGBClassifier(max_depth=10,
min_child_weight=6,
gamma=0.5,
colsample_bytree=0.7,
subsample=0.7,
reg_alpha=1)
xgb.fit(train_data_mix_n, train_Y)
predicted_label = xgb.predict(test_data_mix_n)
print("Test accuracy using XGBoost Classifier")
print(accuracy_score(test_Y, predicted_label))
print("Confusion Metrix for XGBoost Classifier..")
cnf_matrix = confusion_matrix(test_Y, predicted_label)
print(cnf_matrix)
def movie_model_save(variable, Data):
pd.options.mode.chained_assignment = None
contents = pd.DataFrame(Data, columns = ['PAYMENT', 'PROGRAM_TYPE', 'New_Contents', 'genre_Label', 'target_age', 'playtime', 'channel_Label', 'contentnumber', 'episode_count', 'past_view'])
x_train = contents[contents['New_Contents'] == 0]
x_train.loc[:,'PROGRAM_TYPE'] = round(x_train.loc[:,'PROGRAM_TYPE'])
x_train = x_train[x_train['PROGRAM_TYPE'] != x_train.PROGRAM_TYPE.unique()[0]]
x_train.contentnumber = x_train.contentnumber.fillna(0)
x_train.episode_count = x_train.episode_count.fillna(1)
x_train = x_train.drop('New_Contents', axis = 1)
x_train = x_train.drop('PROGRAM_TYPE', axis = 1)
x_train = x_train.values
x_train = x_train.astype('float32')
scaler = MinMaxScaler(feature_range=(0, 1))
x_train = scaler.fit_transform(x_train)
contents = pd.DataFrame(Data, columns = ['PROGRAM_TYPE', 'New_Contents', 'ViewCount'])
y_train = contents[contents['New_Contents'] == 0]
y_train = y_train.drop('New_Contents', axis = 1)
y_train.loc[:,'PROGRAM_TYPE'] = round(y_train.loc[:,'PROGRAM_TYPE'])
y_train = y_train[y_train['PROGRAM_TYPE'] != y_train.PROGRAM_TYPE.unique()[0]]
y_train = y_train.drop('PROGRAM_TYPE', axis = 1)
y_train = y_train.values
y_train = y_train.astype('float32')
import xgboost as xgb
xgb = xgb.XGBRegressor(colsample_bytree = 1,
learning_rate =0.4,
n_estimators=1000,
max_depth=8,
min_child_weight=1,
max_delta_step = 2.5,
gamma=1.0,
subsample=0.8,
objective = 'reg:linear',
n_jobs=8,
scale_pos_weight=1.8,
random_state=27,
base_score = 0.5)
xgb.fit(x_train, y_train)
filename = './data/finalized_model_movie.sav'
pickle.dump(xgb, open(filename, 'wb'))
def xgb_model_1(X_train,y_train,X_test,params=None):
# train with the scikit-learn API
xgb = XGBRegressor(n_estimators=1000, max_depth=13, min_child_weight=150,
subsample=0.7, colsample_bytree=0.3)
y_test = np.zeros(len(X_test))
for i, (train_ind, val_ind) in enumerate(KFold(n_splits=2, shuffle=True,
random_state=1989).split(X_train)):
print("----------------------")
print("Training model #%d" % i)
print("----------------------")
# XGBRegressor.fit
xgb.fit(X_train[train_ind], y_train[train_ind],
eval_set=[(X_train[val_ind], y_train[val_ind])],
early_stopping_rounds=10, verbose=25)
y_test += xgb.predict(X_test, ntree_limit=xgb.best_ntree_limit)
y_test /= 2
return y_test
def pred():
xgb = XGBClassifier(booster='gbtree', gamma=0.0, max_depth=8, min_child_weight=3, learning_rate=0.03, n_jobs=-1,
scale_pos_weight=1, reg_alpha=0.1, reg_lambda=1, colsample_bytree=0.9, subsample=0.8,
n_estimators=370, objective="binary:hinge", tree_method='gpu_hist', gpu_id=0,
random_state=5477113)
xgb.fit(x_combined, y_combined)
y_pred = xgb.predict(X_test)
team_name = 'TeamFOSAI'
submission_index = 2
label_file = '/media/jose/hk-data/PycharmProjects/the_speech/data/mask/labels/labels.csv'
df_labels = pd.read_csv(label_file)
# Write out predictions to csv file (official submission format)
pred_file_name = task + '.' + feat_type +'.test.' + team_name + '_' + str(submission_index) + '.csv'
print('Writing file ' + pred_file_name + '\n')
df = pd.DataFrame(data={'file_name': df_labels['file_name'][df_labels['file_name'].str.startswith('test')].values,
'prediction': le.inverse_transform(y_pred).flatten()},
columns=['file_name','prediction'])
df.to_csv(pred_file_name, index=False)
print('Done.\n')
def train_xgboost(df_train, features, target, save_model=False, cv=False):
# Numerate feature strings for modeling and save feature_ids.
feature_ids = {}
for col in features + ['Ad']:
if df_train[col].dtype == "object":
catigories = list(df_train[col].unique())
df_train[col] = df_train[col].apply(
lambda cat: catigories.index(cat))
feature_ids[col] = {
cat: catigories.index(cat)
for cat in catigories
}
# Fit Gradient Boosted decision model.
X = df_train[features + ['Ad']].as_matrix()
y = df_train[target].as_matrix()
# Declare XGboost model.
xgb = XGBClassifier(learning_rate=0.8,
n_estimators=54,
max_depth=5,
min_child_weight=1,
gamma=0.2,
subsample=0.8,
colsample_bytree=0.75,
reg_alpha=15.25,
objective='binary:logistic')
# Fit the model on the data
xgb.fit(X, y, eval_metric='auc')
# Print 5-fold cross validation scores if cv=True.
if cv:
cv_scores = cross_val_score(xgb, X, y, cv=5)
print 'cross_val_scores:', cv_scores, cv_scores.mean()
return xgb, feature_ids
def xgboost_param_solution():
xgb=XGBoostClassifier(alpha=0, booster='gbtree', colsample_bytree=0.459971793632,
early_stopping_rounds=30, eta=0.0305648288294,
eval_metric='mlogloss', gamma=0.0669039612464, l=0, lambda_bias=0,
max_delta_step=4, max_depth=14, min_child_weight=8, nthread=4,
ntree_limit=0, num_class=9, num_round=1000,
objective='multi:softprob', seed=84425, silent=0,
subsample=0.972607582489, use_buffer=True)
train=load_data('train.csv')
test=load_data('test.csv')
le = preprocessing.LabelEncoder()
le.fit(train['target'])
train['target']=le.transform(train['target'])
feature_cols= [col for col in train.columns if col not in ['target','id']]
X_train=train[feature_cols]
X_test=test[feature_cols]
y=train['target']
test_ids=test['id']
xgb.fit(X_train, y)
preds=xgb.predict_proba(X_test)
write_submission(test_ids,preds,'submissions/xgboost_param_solution_76.csv')
def trainxgb(model_id,train_x,train_y,valid_x,valid_y,test_x):
train_x,train_y=shuffle(train_x,train_y)
random_state=random.randint(0, 1000000)
print('random state: {state}'.format(state=random_state))
xgb = XGBoostClassifier(base_estimator='gbtree',
objective='multi:softprob',
metric='mlogloss',
num_classes=9,
learning_rate=random.uniform(0.01,0.05),
max_depth=random.randint(10,20),
max_samples=random.uniform(0.0,1.0),
max_features=random.uniform(0.0,1.0),
max_delta_step=random.randint(1,10),
min_child_weight=random.randint(1,10),
min_loss_reduction=1,
l1_weight=0.0,
l2_weight=0.0,
l2_on_bias=False,
gamma=0.02,
inital_bias=random.uniform(0.0,1.0),
random_state=random_state,
watchlist=[[valid_x,valid_y]],
n_jobs=30,
n_iter=3000,
)
xgb.fit(train_x, train_y)
valid_predictions = xgb.predict_proba(valid_x)
if test(valid_y,valid_predictions) <0.450:
test_predictions= xgb.predict_proba(test_x)
data.saveData(valid_predictions,"../valid_results/valid_"+str(model_id)+".csv")
data.saveData(test_predictions,"../results/results_"+str(model_id)+".csv")
def run_cv(x_train, x_test, y_train, y_test):
x_train = x_train
conf.xgb_config()
tic = time.time()
data_message = 'X_train.shape={}, X_test.shape = {}'.format(
np.shape(x_train), np.shape(x_test))
print(data_message)
xgb = XGBooster(conf)
best_auc, best_round, cv_rounds, best_model = xgb.fit(x_train, y_train)
print('Training time cost {}s'.format(time.time() - tic))
xgb.save_model()
result_message = 'best_auc = {}, best_round = {}'.format(
best_auc, best_round)
print(result_message)
# now = time.strftime('%Y-%m-%d %H:%M')
result_saved_path = '../result/result_{}-{:.4f}.csv'.format(now, best_auc)
xgb_predict(best_model, x_test, y_test, save_result_path=result_saved_path)
def run_cv(x_train, x_test, y_train, y_test, regress_conf):
x_train = x_train
tic = time.time()
data_message = 'X_train.shape={}, X_test.shape = {}'.format(
np.shape(x_train), np.shape(x_test))
log.logger.info(data_message)
xgb = XGBooster(regress_conf)
best_score, best_round, best_model = xgb.fit(x_train, y_train)
log.logger.info('Training time cost {}s'.format(time.time() - tic))
# xgb.save_model()
result_message = 'best_score = {}, best_round = {}'.format(
best_score, best_round)
log.logger.info(result_message)
# now = time.strftime('%Y-%m-%d %H:%M')
result_saved_path = '../result/result_{}-{:.4f}.csv'.format(
now, best_round)
# xgb_predict(best_model, x_test, y_test, result_save_path=result_saved_path)
xgb_predict(best_model, x_test, y_test, result_save_path=None)
def select_features_from_xgb(features,labels,test_feature):
print("\nStart selecting importance features")
xgb = XGBClassifier(n_estimators=2, max_depth=4, learning_rate = 0.07, subsample = 0.8, colsample_bytree = 0.9)
xgb = xgb.fit(features, labels)
importances = xgb.feature_importances_
indices = np.argsort(importances)[::-1]
model = SelectFromModel(xgb, prefit=True)
features_new = model.transform(features)
test_feature_new = model.transform(test_feature)
with open(data_path + "importance_features.txt" , "w") as log:
for f in range(features_new.shape[1]):
log.write(str(f + 1) + "." + " feature " + str(indices[f]) + " " + str(importances[indices[f]]) + "\n")
#print("%d. feature %d (%f)" % (f + 1, indices[f], importances[indices[f]]))
print("Features selection done saved new data in data path")
sel = VarianceThreshold(threshold = (.8 * (1 - .8)))
sel.fit_transform(features)
return features_new, test_feature_new
x_test_stacking.iloc[i, 3] = x_test_stacking.iloc[i, 3] + pred_rf[i]
x_test_stacking.iloc[i, 4] = x_test_stacking.iloc[i, 4] + pred_knn[i]
#------------------------------------------------------------------
#####################对测试集结果进行平均化处理#####33
print(x_test_stacking)
for i in range(len(x_test)):
for j in range(5):
x_test_stacking.iloc[i, j] = x_test_stacking.iloc[i, j] / 3
print(x_test_stacking)
###################################第二层用xgboost#############
xgb = XGBRegressor(max_depth=4,
learning_rate=0.005,
n_estimators=500,
silent=True,
objective='reg:linear',
subsample=0.93,
base_score=y_mean,
seed=0,
missing=None)
xgb.fit(x_train_stacking, y_train)
pred = xgb.predict(x_test_stacking)
print(pred)
output = pd.DataFrame({'id': test['ID'].astype(np.int32), 'y': pred})
output.to_csv(
'C:\\Users\\Administrator\\Desktop\\benz\\new\\test_stacking.csv',
index=False)
# ## XG BOOST ON SMOTE
# In[127]:
import xgboost as xgb
# In[128]:
from xgboost import XGBClassifier
tree_range = range(2, 30, 5)
score1 = []
score2 = []
for tree in tree_range:
xgb = XGBClassifier(n_estimators=tree)
xgb.fit(X_smote, y_smote)
score1.append(xgb.score(X_smote, y_smote))
score2.append(xgb.score(X_test, y_test))
get_ipython().run_line_magic('matplotlib', 'inline')
plt.plot(tree_range, score1, label='Accuracy on training set')
plt.plot(tree_range, score2, label='Accuracy on testing set')
plt.xlabel('Value of number of trees in XGboost')
plt.ylabel('Accuracy')
plt.legend()
# As we can see accuracy is increasing for the test and stabilizes at one point
# In[129]:
xgb = XGBClassifier(n_estimators=18)
toc6 = time.time()
print('Elapsed time for Neural network is %f seconds \n' % float(toc6 - tic6))
#--------------- XGBoost algorithm
import xgboost as xgb
from xgboost.sklearn import XGBClassifier
tic7 = time.time()
xgb = XGBClassifier(objective='multi:softmax',
num_class=4,
n_fold=4,
colsample_bytree=1,
learning_rate=0.15,
max_depth=5,
n_estimators=600,
subsample=0.3)
xgb.fit(X_train, y_train)
y_pred = xgb.predict(X_test)
# Get the accuracy score
acc = accuracy_score(y_test, y_pred)
# Get f1 score
f1_xgb = f1_score(y_test, y_pred, average='weighted')
# Append to the accuracy list
#accuracy_lst.append(acc)
#f1_lst.append(f1_xgb)
print("[XGBoost algorithm] accuracy_score: {:.3f}.".format(acc))
print("[XGBoost algorithm] f1_score: {:.3f}.".format(f1_xgb))
dtest = xgb.DMatrix(x_test)
cv_output = xgb.cv(xgb_params, dtrain, num_boost_round=1000, early_stopping_rounds=20,verbose_eval=50, show_stdv=False)
cv_output[['train-rmse-mean', 'test-rmse-mean']].plot()
num_boost_rounds = len(cv_output)
model = xgb.train(dict(xgb_params, silent=0), dtrain, num_boost_round= num_boost_rounds)
xgb.plot_importance(model, height=0.5)
num_boost_round = model.best_iteration
xgb.plot_importance(model, height=0.5)
from xgboost.sklearn import XGBRegressor
xgb = XGBRegressor( nthread=-1, missing= -1, n_estimators=300, learning_rate=0.02, max_depth=17, subsample=0.9
, min_child_weight=3, colsample_bytree=0.7, reg_alpha=100, reg_lambda=100, silent=False)
xgb.fit(x_train,y_train)
#print(x_train)
pred=xgb.predict(x_test)
predictions = [round(value) for value in pred]
"""x_test['result']=pred
x_test['crop']=y_test
x_test.to_csv('pred.csv')"""
#print accuracy_score(y_test,pred)
accuracy = accuracy_score(y_test, predictions)
print("Accuracy: %.2f%%" % (accuracy * 100.0))
@app.route('/predictor',methods=['POST','GET'])
def predictor():
data=request.get_json(force=True)
a=str(data.get("rain"))
b=str(data.get("temperature"))
'Supermarket Type3': 2,
'Supermarket Type2': 1
}
datatest.Outlet_Type = [gender[item] for item in datatest.Outlet_Type]
datatest.head()
#usig Randome forest Regresser
regr = RandomForestRegressor(max_depth=2, random_state=0, n_estimators=500)
regr.fit(data[data.columns[1:6]], data["Item_Outlet_Sales"])
datat.dtypes
pred = regr.predict(datatest[datatest.columns[1:6]])
#using Xgboost
xgb = xgb.XGBRegressor(n_estimators=50,
learning_rate=0.09,
gamma=0,
subsample=0.85,
colsample_bytree=1,
max_depth=7)
xgb.fit(data[data.columns[1:6]], data["Item_Outlet_Sales"])
pred = xgb.predict(datatest[datatest.columns[1:6]])
datat["Item_Outlet_Sales"] = pred
newdf = datat[['Item_Identifier', 'Outlet_Identifier', 'Item_Outlet_Sales']]
newdf.to_csv("D://24projects//Project 3//output.csv",
encoding='utf-8',
index=False)
datat["Item_Outlet_Sales"].isnull().sum()
features1 = scaler.fit_transform(features1) from sklearn.model_selection import train_test_split X_train, X_test, y_train, y_test = train_test_split(features1, target, test_size=0.1, random_state=42) from sklearn import svm svm1 = svm.SVC() svm1.fit(X_train, y_train) predictionssvm = svm1.predict(X_test) dtc=DecisionTreeClassifier() modeldtc = dtc.fit(X_train, y_train) predictionsdtc = dtc.predict(X_test) adb=AdaBoostClassifier() modeladb=adb.fit(X_train, y_train) predictionsadb = adb.predict(X_test) from sklearn.ensemble import GradientBoostingClassifier xgb= GradientBoostingClassifier() modelxbg=xgb.fit(X_train, y_train) predictionsxgb = xgb.predict(X_test) import operator from sklearn.neural_network import MLPClassifier mlp=MLPClassifier(solver='adam',activation='tanh',random_state=0) modelmlp=mlp.fit(X_train,y_train) predictionmlp=mlp.predict(X_test) #4. Stacked Classifier X=features1 y=target clf1 = adb clf2 = dtc clf3 = svm1 meta = LogisticRegression()
def calculateRankMatrix(train_data_mix, train_Y, colnames, threshold):
ranks = {}
clf = ExtraTreesClassifier()
clf = clf.fit(train_data_mix, train_Y)
ranks["tree"] = YoungPeopleEmpathy.ranking(clf.feature_importances_,
colnames)
xgb = XGBClassifier(max_depth=10,
min_child_weight=8,
gamma=0.7,
colsample_bytree=0.7,
subsample=0.7,
reg_alpha=1)
xgb = xgb.fit(train_data_mix, train_Y)
ranks["xgb"] = YoungPeopleEmpathy.ranking(xgb.feature_importances_,
colnames)
ada = AdaBoostClassifier(DecisionTreeClassifier(max_depth=2),
n_estimators=600,
learning_rate=1)
ada = ada.fit(train_data_mix, train_Y)
ranks["ada"] = YoungPeopleEmpathy.ranking(ada.feature_importances_,
colnames)
model = LogisticRegression()
# create the RFE model and select 3 attributes
rfe = RFE(model, 3)
rfe = rfe.fit(train_data_mix, train_Y)
#column names sorted by ranking
ranks["RFE"] = YoungPeopleEmpathy.ranking(list(map(
float, rfe.ranking_)),
colnames,
order=-1)
rf = RandomForestClassifier(bootstrap=True,
class_weight=None,
criterion='gini',
max_depth=10,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
min_samples_leaf=1,
min_samples_split=2,
min_weight_fraction_leaf=0.0,
n_estimators=100,
n_jobs=1,
oob_score=False,
random_state=None,
verbose=0,
warm_start=False)
rf.fit(train_data_mix, train_Y)
ranks["RF"] = YoungPeopleEmpathy.ranking(rf.feature_importances_,
colnames)
r = {}
for name in colnames:
r[name] = round(
np.mean([ranks[method][name] for method in ranks.keys()]), 2)
methods = sorted(ranks.keys())
ranks["Mean"] = r
methods.append("Mean")
#print("\t%s" % "\t".join(methods))
#for name in colnames:
# print("%s\t%s" % (name, "\t".join(map(str,
# [ranks[method][name] for method in methods]))))
# Put the mean scores into a Pandas dataframe
meanplot = pd.DataFrame(list(r.items()),
columns=['Feature', 'Mean Ranking'])
# Sort the dataframe
meanplot = meanplot.sort_values('Mean Ranking', ascending=False)
return meanplot
import xgboost as xgb
from xgboost import XGBRegressor
xgb = XGBRegressor(learning_rate=0.01,
n_estimators=3460,
max_depth=3,
min_child_weight=0,
gamma=0,
subsample=0.7,
colsample_bytree=0.7,
objective='reg:linear',
nthread=4,
scale_pos_weight=1,
seed=27,
reg_alpha=0.00006)
xgb_fit = xgb.fit(x_train, y_train)
#----------------------svm
from sklearn import svm
svr_opt = svm.SVR(C=100000, gamma=1e-08)
svr_fit = svr_opt.fit(x_train, y_train)
cv_rmse(svr_fit).mean
#-----------------LGBMRegressor
from lightgbm import LGBMRegressor
lgbm_model = LGBMRegressor(objective='regression',
num_leaves=5,
learning_rate=0.05,
n_estimators=720,
'''
{'colsample_bytree': 0.5,
'gamma': 0.15,
'learning_rate': 0.1,
'max_delta_step': 0,
'max_depth': 6,
'n_estimators': 27,
'subsample': 0.45}
'''
xgb.best_score_ # 0.83585339132974634
xgb = XGBClassifier(max_depth=6, learning_rate=0.1, n_estimators=27,
objective='multi:softprob', subsample=0.4, colsample_bytree=0.5, seed=0)
xgb.fit(X, y)
xgb_predictions = xgb.predict_proba(X_test)
# Put these in a good form to spit out
xgb_predictions = xgb_predictions.ravel()
# Have to ensure these are in the same order, yep, looks good
classes = np.tile(xgb.classes_, X_test.shape[0])
ids = np.repeat(test["id"].values, 12)
print(xgb_predictions.shape)
print(classes.shape)
print(ids.shape)
print(test_users['id'].shape)
print(test['id'].shape)
import pandas as pd
dataset= pd.read_csv('C:/Users/Riahi/Desktop/PROJET_PATIE_ML/BD_Projet_NEW112- Copie.csv', delimiter=';')
price=dataset['COST']
Data=dataset.drop(['COST'],axis=1)
x=np.array(price).reshape(-1,1)
from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test=train_test_split(Data,x,test_size=0.33,random_state=0)
import xgboost as xgb
xgb = xgb.XGBRegressor(n_estimators=10, max_depth=5, objectives = 'reg:linear' , learning_rate=0.3)
import time
dep=time.time()
xgb.fit(X_train,Y_train)
fin=time.time()-dep
predictions = xgb.predict(X_test)
from sklearn.metrics import mean_squared_error
rmse=np.sqrt(mean_squared_error(Y_test,predictions))
print("RMSE: %f" % (rmse))
from sklearn.metrics import explained_variance_score
EV=explained_variance_score(Y_test,predictions)
print("EV : %f" %(EV))
import matplotlib.pyplot as plt
import os
os.getcwd()
os.chdir('C:/Program Files (x86)/Graphviz2.38/bin')
xgb.plot_tree(xgb,num_trees=9)
plt.rcParams['figure.figsize'] = [50, 10]
T_train_sample_xgb = xgb.DMatrix(X_train_sample, Y_train_sample)
X_test_sample_xgb = xgb.DMatrix(X_test_sample)
xgb = XGBClassifier(max_depth=6, learning_rate=0.1, n_estimators=200,
objective='multi:softprob', subsample=0.5, colsample_bytree=0.5, seed=0)
#scores: XGBClassifier(max_depth=6, learning_rate=0.1, n_estimators=50
#0.8183974444336767 121 rounds
Y_test_sample = test_sample["country_destination"]
Y_test_sample = Y_test_sample.map(country_num_dic)
X_train_sample.isnull().sum()
eval_set = [(X_train_sample, Y_train_sample), (X_test_sample, Y_test_sample)]
xgb.fit(X_train_sample, Y_train_sample, eval_set = eval_set, eval_metric = 'mlogloss', early_stopping_rounds= 10)
Y_pred_sample = xgb.predict_proba(X_test_sample)
y_le_train_sample = (train_sample['country_destination'].map(country_num_dic)).values
y_le_test_sample = (test_sample['country_destination'].map(country_num_dic)).values
y_le_train = (train['country_destination'].map(country_num_dic)).values
id_train = train['id'].values
id_train_sample = train_sample['id'].values
id_test_sample = test_sample['id'].values
id_test = test['id'].values
#------------- TRAIN SAMPLE PREDICTION --------------------------
ids = [] #list of ids