Skip to content

F
ffm-baseline
Commit 5d5ac927 authored by 高雅喆's avatar 高雅喆
Browse files
Options

Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline 

change data dir to /home/gaoyazhe/
parents 7622f47e eb4e1fe6
Hide whitespace changes
Inline Side-by-side
Showing with 18 additions and 51 deletions
tensnsorflow/ffm.py
View file @ 5d5ac927
......@@ -161,54 +161,37 @@ def get_data():
df = df.drop("z", axis=1)
df = pd.merge(df,get_statistics(),how='left',on = "device_id").fillna(0)
df = df.drop("device_id", axis=1)
print(df.head())
print(df.head(2))
return df,validate_date,ucity_id,cid
def transform(a,validate_date):
model = multiFFMFormatPandas()
df = model.fit_transform(a, y="y", n=160000, processes=18)
df = model.fit_transform(a, y="y", n=160000, processes=25)
df = pd.DataFrame(df)
df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
df["city_id"] = df[0].apply(lambda x: x.split(",")[2])
df["cid"] = df[0].apply(lambda x: x.split(",")[3])
df["number"] = np.random.randint(1, 2147483647, df.shape[0])
df["seq"] = list(range(df.shape[0]))
df["seq"] = df["seq"].astype("str")
df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[4:]))
df["data"] = df["seq"].str.cat(df["data"], sep=",")
df["number"] = np.random.randint(1, 2147483647, df.shape[0])
df = df.drop([0,"seq"], axis=1)
print(df.head())
print(df.head(2))
train = df[df["stat_date"] != validate_date]
train = train.drop("stat_date",axis=1)
test = df[df["stat_date"] == validate_date]
test = test.drop("stat_date",axis=1)
print("train shape")
print(train.shape)
yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
pd.io.sql.to_sql(train, "train_zhao", yconnect, schema='jerry_test', if_exists='replace', index=False)
print("train insert done")
pd.io.sql.to_sql(test, "test_zhao", yconnect, schema='jerry_test', if_exists='replace', index=False)
print("test insert done")
# print("train shape")
# print(train.shape)
train.to_csv(path + "train.csv", sep="\t", index=False)
test.to_csv(path + "test.csv", sep="\t", index=False)
return model
# n = 100000
# for i in range(0,df.shape[0],n):
# print(i)
# if i == 0:
# temp = df.loc[0:n]
# elif i+n > df.shape[0]:
# temp = df.loc[i+1:]
# else:
# temp = df.loc[i+1:i+n]
# pd.io.sql.to_sql(temp, table, yconnect, schema='jerry_test', if_exists='append', index=False)
# print("insert done")
def get_statistics():
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='eagle')
sql = "select device_id,total,精选,直播,鼻部,眼部,微整,牙齿,轮廓,美肤抗衰," \
......@@ -222,6 +205,7 @@ def get_statistics():
df = df.drop("total", axis=1)
return df
def get_predict_set(ucity_id, cid,model):
db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
sql = "select device_id,y,z,stat_date,ucity_id,cid_id,clevel1_id,ccity_name,label from esmm_pre_data"
......@@ -245,49 +229,32 @@ def get_predict_set(ucity_id, cid,model):
print("df ok")
print(df.shape)
print(df.head(2))
df = model.transform(df,n=160000, processes=18)
df = model.transform(df,n=160000, processes=25)
df = pd.DataFrame(df)
df["label"] = df[0].apply(lambda x: x.split(",")[0])
df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
df["city_id"] = df[0].apply(lambda x: x.split(",")[2])
df["cid"] = df[0].apply(lambda x: x.split(",")[3])
df["number"] = np.random.randint(1, 2147483647, df.shape[0])
df["seq"] = list(range(df.shape[0]))
df["seq"] = df["seq"].astype("str")
df["data"] = df[0].apply(lambda x: ",".join(x.split(",")[4:]))
df["data"] = df["seq"].str.cat(df["data"], sep=",")
df["number"] = np.random.randint(1, 2147483647, df.shape[0])
df = df.drop([0, "seq"], axis=1)
print(df.head())
native_pre = df[df["label"] == "0"]
native_pre = native_pre.drop("label", axis=1)
print("native_pre shape")
print(native_pre.shape)
native_pre.to_csv(path+"native_pre.csv",sep="\t",index=False)
# print("native_pre shape")
# print(native_pre.shape)
nearby_pre = df[df["label"] == "1"]
nearby_pre = nearby_pre.drop("label", axis=1)
print("nearby_pre shape")
print(nearby_pre.shape)
yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
pd.io.sql.to_sql(native_pre, "native_zhao", yconnect, schema='jerry_test', if_exists='replace', index=False)
print("train insert done")
pd.io.sql.to_sql(nearby_pre, "nearby_zhao", yconnect, schema='jerry_test', if_exists='replace', index=False)
print("test insert done")
# df = pd.DataFrame(df)
# df["stat_date"] = df[0].apply(lambda x: x.split(",")[0])
# df["device_id"] = df[0].apply(lambda x: x.split(",")[1])
# df["city_id"] = df[0].apply(lambda x: x.split(",")[2])
# df["diary_id"] = df[0].apply(lambda x: x.split(",")[3])
# df["seq"] = list(range(df.shape[0]))
# df["seq"] = df["seq"].astype("str")
# df["ffm"] = df[0].apply(lambda x: ",".join(x.split(",")[4:]))
# df["ffm"] = df["seq"].str.cat(df["ffm"], sep=",")
# df["random"] = np.random.randint(1, 2147483647, df.shape[0])
# df = df.drop([0,"seq"], axis=1)
# print(df.head())
nearby_pre.to_csv(path + "nearby_pre.csv", sep="\t", index=False)
# print("nearby_pre shape")
# print(nearby_pre.shape)
if __name__ == "__main__":
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment