lr.fit(Xi_train, Xv_train, y_train, Xi_valid, Xv_valid, y_valid)
elif algo == 'fm':
fm_params = {
"feature_size": feature_size,
"field_size": field_size,
"embedding_size": 15,
"epoch": 20,
"batch_size": 1024,
"learning_rate": 0.001,
"optimizer_type": "adam",
"l2_w_reg": 0.01,
"l2_v_reg": 0.01,
"verbose": True
}
fm = FM(**fm_params)
fm.fit(Xi_train, Xv_train, y_train, Xi_valid, Xv_valid, y_valid)
elif algo == 'deepfm':
deepfm_params = {
"feature_size": feature_size,
"field_size": field_size,
"embedding_size": 15,
"deep_layers": [256, 128, 64],
"epoch": 20,
"batch_size": 1024,
"learning_rate": 0.001,
"optimizer_type": "adam",
"l2_reg": 0.01,
"dropout_deep": [0.5, 0.5, 0.5, 0.5],
"verbose": True
}
deepfm = DeepFM(**deepfm_params)
test_size=0.2,
random_state=42)
y_train = y_train.values.reshape((-1, 1))
y_test = y_test.values.reshape((-1, 1))
#model=LR(features_sizes,loss_type='rmse')#,hash_size=r)
#model=FM(features_sizes,k=24)
#model=MLP(features_sizes,deep_layers=(12,12),k=24) best(12,12) k=24
#model=FM(features_sizes,k=24,FM_ignore_interaction=[(0,2),(0,3),(0,4)])
model = FM(features_sizes,
k=24,
FM_ignore_interaction=[(0, 1), (0, 2), (0, 3), (0, 4)])
#model=DeepFM(features_sizes,deep_layers=(12,12),k=24)
#model = NFM(features_sizes, k=24)
print(model)
best_score = model.fit(X_train,
X_test,
y_train,
y_test,
lr=0.0005,
N_EPOCH=50,
batch_size=5000,
early_stopping_rounds=5) #0.0005->0.001(1e-3 bs=1000)
'''
ls=[]
Rounds=1
for _ in range(Rounds):
ls.append(best_score)
print(model)
print(" Protocol Test Result : \n%.4f %.4f %s" % (pd.Series(ls).mean(),pd.Series(ls).min(),str([round(i,4) for i in ls])))
'''
import pandas as pd
import numpy as np
from models import LR,FM,MLP,WideAndDeep,DeepFM
if __name__=='__main__':
np.random.seed(2019)
data_dir="../data/movie_lens_100k/"
train = pd.read_csv(data_dir+'ua.base', sep='\t', names=['user_id', 'movie_id', 'ratings', 'time'])
test = pd.read_csv(data_dir+'ua.test', sep='\t', names=['user_id', 'movie_id', 'ratings', 'time'])
data=pd.concat([train,test],axis=0)
y_train = train['ratings'].values.reshape(-1, 1) # 一列
y_test = test['ratings'].values.reshape(-1, 1)
features=['user_id','movie_id']
features_sizes=[data[f].nunique() for f in features]
print("DFM")
ls=[]
model=LR
for _ in range(10):
model=FM(features_sizes)
#model = LR(features_sizes)
#model=DeepFM(features_sizes,deep_layers=(10,10),k=10)
best_score=model.fit(train[features]-1,test[features]-1,y_train,y_test,lr=0.0005,N_EPOCH=150,batch_size=500,early_stopping_rounds=30)
#-1是因为ids要从0起.而数据中是从1起的
ls.append(best_score)
print(pd.Series(ls).mean(),pd.Series(ls).min())
print(str(ls))
y_test=y_test.values.reshape((-1,1))
'''
#<Model>
#model=LR(features_sizes,loss_type='binary',metric_type='auc')
model=FM(features_sizes,k=8,loss_type='binary',metric_type='auc')
#model=FM(features_sizes,k=8,loss_type='binary',metric_type='auc',FM_ignore_interaction=[(0,2),(0,3),(0,4)]) #FMDE
#model=MLP(features_sizes,k=8,loss_type='binary',metric_type='auc',deep_layers=(32,8))
#model=NFM(features_sizes,k=8,loss_type='binary',metric_type='auc')
#model=WideAndDeep(features_sizes,k=8,loss_type='binary',metric_type='auc',deep_layers=(8,8))
#model=DeepFM(features_sizes,k=8,loss_type='binary',metric_type='auc',deep_layers=(8,8))
#model=AFM(features_sizes,k=8,loss_type='binary',metric_type='auc',attention_FM=8)
#model=DeepAFM(features_sizes,k=8,loss_type='binary',metric_type='auc',attention_FM=8,deep_layers=(8,8))
print(model)
#[BUG fix] 老版本一定要传入拷贝..wtf~! 06/27修补BUG 内部copy防止影响数据
best_score = model.fit(X_train[train_features], X_test[train_features], y_train, y_test, lr=0.0005, N_EPOCH=50, batch_size=4096,early_stopping_rounds=5)#0.0005->0.001(1e-3 bs=1000)
y_pred=model.predict(X_test)
y_pred=1./(1.+np.exp(-1.*y_pred))#sigmoid transform
from sklearn.metrics import roc_auc_score,log_loss
print("ROC-AUC score on valid set: %.4f" %roc_auc_score(y_test,y_pred))
#print(log_loss(y_test,y_pred))
test_data_=pd.concat([test_data_new_msno,test_data_new_song,test_data_old],axis=0).copy()
for i,c in enumerate(train_features):
enc = encs[i]
test_data_[c] = enc.transform(test_data_[c])
y_pred_test=model.predict(test_data_[train_features])
y_pred_test=1./(1.+np.exp(-1.*y_pred_test))#sigmoid transform
print("ROC-AUC score on test set: %.4f" %roc_auc_score(test_data_['target'],y_pred_test))