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

eda/esmm/Model_pipline/sort_and_2sql.py

@@ -18,9 +18,11 @@ def con_sql(sql):
     db.close()
     return result
 
+
 def set_join(lst):
-    # return ','.join([str(i) for i in list(lst)])
-    return ','.join([str(i) for i in lst.unique().tolist()])
+    r = [str(i) for i in lst.unique().tolist()]
+    r =r[:500]
+    return ','.join(r)
 
 def main():
 
@@ -73,7 +75,7 @@ def main():
         cur = con.cursor()
         cur.execute(delete_str)
         con.commit()
-        df_all.to_sql('esmm_device_diary_queue',con=engine,if_exists='append',index=False)
+        df_all.to_sql('esmm_device_diary_queue',con=engine,if_exists='append',index=False,chunksize=8000)
     except Exception as e:
         print(e)
 

tensnsorflow/cid_time_cut.py

+import pandas as pd
+import pymysql
+from sqlalchemy import create_engine
+
+
+def con_sql(db,sql):
+    cursor = db.cursor()
+    try:
+        cursor.execute(sql)
+        result = cursor.fetchall()
+        df = pd.DataFrame(list(result))
+    except Exception:
+        print("发生异常", Exception)
+        df = pd.DataFrame()
+    finally:
+        db.close()
+    return df
+
+
+def cut_map(x):
+    if 0 < x <= 5:
+        return 2
+    elif 5 < x <= 10:
+        return 3
+    elif 10 < x <= 15:
+        return 4
+    elif 15 < x <= 20:
+        return 5
+    elif 20 < x <= 40:
+        return 6
+    else:
+        return 7
+
+
+def cut():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select cid_id,time from cid_time"
+    df = con_sql(db, sql)
+    df = df.rename(columns={0: "cid", 1: "time"})
+    print(df.shape)
+    part_1 = df.loc[df["time"] == 0]
+    part_2 = df.loc[df["time"] != 0]
+    part_1["time"] = 1
+    part_2["time"] = part_2["time"].map(cut_map)
+    merge = part_1.append(part_2)
+    print(merge.shape)
+    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
+    pd.io.sql.to_sql(merge, "cid_time_cut", yconnect, schema='jerry_test', if_exists='replace', index=False)
+
+if __name__ == "__main__":
+    cut()
+
+
+
+
+
+

tensnsorflow/es/feature.py

+
+import pandas as pd
+import pymysql
+import datetime
+
+
+def con_sql(db,sql):
+    cursor = db.cursor()
+    try:
+        cursor.execute(sql)
+        result = cursor.fetchall()
+        df = pd.DataFrame(list(result))
+    except Exception:
+        print("发生异常", Exception)
+        df = pd.DataFrame()
+    finally:
+        db.close()
+    return df
+
+
+def get_data():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select max(stat_date) from esmm_train_data"
+    validate_date = con_sql(db, sql)[0].values.tolist()[0]
+    print("validate_date:" + validate_date)
+    temp = datetime.datetime.strptime(validate_date, "%Y-%m-%d")
+    start = (temp - datetime.timedelta(days=60)).strftime("%Y-%m-%d")
+    print(start)
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select e.y,e.z,e.stat_date,e.ucity_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel,c.top,cl.l1,cl.l2,e.device_id,cut.time " \
+          "from esmm_train_data e left join user_feature u on e.device_id = u.device_id " \
+          "left join cid_type_top c on e.device_id = c.device_id " \
+          "left join cid_level2 cl on e.cid_id = cl.cid " \
+          "left join cid_time_cut cut on e.cid_id = cut.cid " \
+          "where e.stat_date >= '{}'".format(start)
+    df = con_sql(db, sql)
+    # print(df.shape)
+    df = df.rename(columns={0: "y", 1: "z", 2: "stat_date", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "l1",11: "l2",
+                            12: "device_id", 13: "time"})
+    print("esmm data ok")
+    # print(df.head(2)
+    print("before")
+    print(df.shape)
+    print("after")
+    df = df.drop_duplicates()
+    df = df.drop_duplicates(["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                             "channel", "top", "l1","l2", "time", "stat_date"])
+    print(df.shape)
+
+    unique_values = []
+    features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                "channel", "top", "time", "stat_date"]
+    for i in features:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        # 下面这行代码是为了区分不同的列中有相同的值
+        df[i] = df[i] + i
+        unique_values.extend(list(df[i].unique()))
+    for i in ["l1","l2"]:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        # l1和l2中的值与top类别是一个类别
+        df[i] = df[i]+"top"
+        unique_values.extend(list(df[i].unique()))
+
+    print("features:")
+    print(len(unique_values))
+    print(df.head(2))
+
+    temp = list(range(1,len(unique_values)+1))
+    value_map = dict(zip(unique_values,temp))
+
+    df = df.drop("device_id", axis=1)
+    train = df
+    test = df[df["stat_date"] == validate_date+"stat_date"]
+    for i in ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                "channel", "top", "l1", "time", "stat_date","l2"]:
+        train[i] = train[i].map(value_map)
+        test[i] = test[i].map(value_map)
+
+    print("train shape")
+    print(train.shape)
+    print("test shape")
+    print(test.shape)
+
+    write_csv(train, "tr",100000)
+    write_csv(test, "va",80000)
+
+    return validate_date,value_map
+
+
+def write_csv(df,name,n):
+    for i in range(0, df.shape[0], n):
+        if i == 0:
+            temp = df.iloc[0:n]
+        elif i + n > df.shape[0]:
+            temp = df.iloc[i:]
+        else:
+            temp = df.iloc[i:i + n]
+        temp.to_csv(path + name+ "/{}_{}.csv".format(name,i), index=False)
+
+
+def get_predict(date,value_map):
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    sql = "select e.y,e.z,e.label,e.ucity_id,e.clevel1_id,e.ccity_name," \
+          "u.device_type,u.manufacturer,u.channel,c.top,cl.l1,cl.l2,e.device_id,e.cid_id,cut.time " \
+          "from esmm_pre_data e left join user_feature u on e.device_id = u.device_id " \
+          "left join cid_type_top c on e.device_id = c.device_id " \
+          "left join cid_level2 cl on e.cid_id = cl.cid " \
+          "left join cid_time_cut cut on e.cid_id = cut.cid where device_id = '358035085192742'"
+    df = con_sql(db, sql)
+    df = df.rename(columns={0: "y", 1: "z", 2: "label", 3: "ucity_id", 4: "clevel1_id", 5: "ccity_name",
+                            6: "device_type", 7: "manufacturer", 8: "channel", 9: "top", 10: "l1",11:"l2",
+                            12: "device_id", 13: "cid_id", 14: "time"})
+
+    df["stat_date"] = date
+
+    print("predict shape")
+    print(df.shape)
+    df["uid"] = df["device_id"]
+    df["city"] = df["ucity_id"]
+    features = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                "channel", "top", "time", "stat_date"]
+    for i in features:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        df[i] = df[i] + i
+    for i in ["l1","l2"]:
+        df[i] = df[i].astype("str")
+        df[i] = df[i].fillna("lost")
+        # l1和l2中的值与top类别是一个类别
+        df[i] = df[i]+"top"
+
+    native_pre = df[df["label"] == 0]
+    native_pre = native_pre.drop("label", axis=1)
+    nearby_pre = df[df["label"] == 1]
+    nearby_pre = nearby_pre.drop("label", axis=1)
+
+    for i in ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                "channel", "top", "l1", "time", "stat_date","l2"]:
+        native_pre[i] = native_pre[i].map(value_map)
+        # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
+        native_pre[i] = native_pre[i].fillna(0)
+
+        nearby_pre[i] = nearby_pre[i].map(value_map)
+        # TODO 没有覆盖到的类别会处理成na，暂时用0填充，后续完善一下
+        nearby_pre[i] = nearby_pre[i].fillna(0)
+
+
+    print("native")
+    print(native_pre.shape)
+    print(native_pre.head())
+    native_pre[["uid","city","cid_id"]].to_csv(path+"native.csv",index=False)
+    write_csv(native_pre, "native",200000)
+
+    print("nearby")
+    print(nearby_pre.shape)
+    print(nearby_pre.head())
+    nearby_pre[["uid","city","cid_id"]].to_csv(path+"nearby.csv",index=False)
+    write_csv(nearby_pre, "nearby", 160000)
+
+
+if __name__ == '__main__':
+    path = "/home/gmuser/esmm_data/"
+    date,value = get_data()
+    get_predict(date, value)
+

tensnsorflow/es/pipeline.sh

+#! /bin/bash
+
+PYTHON_PATH=/home/gaoyazhe/miniconda3/bin/python
+MODEL_PATH=/srv/apps/ffm-baseline/tensnsorflow/es
+DATA_PATH=/home/gmuser/esmm_data
+
+echo "rm leave tfrecord"
+rm ${DATA_PATH}/tr/*
+rm ${DATA_PATH}/va/*
+rm ${DATA_PATH}/native/*
+rm ${DATA_PATH}/nearby/*
+rm -r ${DATA_PATH}/model_ckpt/DeepCvrMTL/201*
+
+echo "data"
+${PYTHON_PATH} ${MODEL_PATH}/feature.py > ${DATA_PATH}/infer.log
+
+echo "csv to tfrecord"
+${PYTHON_PATH} ${MODEL_PATH}/to_tfrecord.py --input_dir=${DATA_PATH}/tr/ --output_dir=${DATA_PATH}/tr/
+${PYTHON_PATH} ${MODEL_PATH}/to_tfrecord.py --input_dir=${DATA_PATH}/va/ --output_dir=${DATA_PATH}/va/
+${PYTHON_PATH} ${MODEL_PATH}/to_tfrecord.py --input_dir=${DATA_PATH}/native/ --output_dir=${DATA_PATH}/native/
+${PYTHON_PATH} ${MODEL_PATH}/to_tfrecord.py --input_dir=${DATA_PATH}/nearby/ --output_dir=${DATA_PATH}/nearby/
+
+cat ${DATA_PATH}/tr/*.tfrecord > ${DATA_PATH}/tr/tr.tfrecord
+cat ${DATA_PATH}/va/*.tfrecord > ${DATA_PATH}/va/va.tfrecord
+cat ${DATA_PATH}/native/*.tfrecord > ${DATA_PATH}/native/native.tfrecord
+cat ${DATA_PATH}/nearby/*.tfrecord > ${DATA_PATH}/nearby/nearby.tfrecord
+
+rm ${DATA_PATH}/tr/tr_*
+rm ${DATA_PATH}/va/va_*
+rm ${DATA_PATH}/native/native_*
+rm ${DATA_PATH}/nearby/nearby_*
+
+
+echo "train..."
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.9 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=2 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=1460 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH} --task_type=train
+
+
+echo "infer native..."
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.9 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=1460 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/native --task_type=infer > ${DATA_PATH}/infer.log
+
+
+echo "infer nearby..."
+${PYTHON_PATH} ${MODEL_PATH}/train.py --ctr_task_wgt=0.9 --learning_rate=0.0001 --deep_layers=512,256,128,64,32 --dropout=0.3,0.3,0.3,0.3,0.3 --optimizer=Adam --num_epochs=1 --embedding_size=16 --batch_size=1024 --field_size=11 --feature_size=1460 --l2_reg=0.005 --log_steps=100 --num_threads=36 --model_dir=${DATA_PATH}/model_ckpt/DeepCvrMTL/ --data_dir=${DATA_PATH}/nearby --task_type=infer > ${DATA_PATH}/infer.log
+
+echo "sort and 2sql"
+${PYTHON_PATH} ${MODEL_PATH}/to_database.py

tensnsorflow/es/to_database.py

+#coding=utf-8
+
+from sqlalchemy import create_engine
+import pandas as pd
+import pymysql
+import MySQLdb
+import time
+
+def con_sql(sql):
+    """
+    :type sql : str
+    :rtype : tuple
+    """
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+    cursor = db.cursor()
+    cursor.execute(sql)
+    result = cursor.fetchall()
+    db.close()
+    return result
+
+
+def nearby_set_join(lst):
+    # return ','.join([str(i) for i in list(lst)])
+    return ','.join([str(i) for i in lst.unique().tolist()])
+
+
+def native_set_join(lst):
+    l = lst.unique().tolist()
+    d = int(len(l)/2)
+    if d == 0:
+        d = 1
+    r = [str(i) for i in l]
+    r =r[:d]
+    return ','.join(r)
+
+
+def main():
+
+    # native queue
+    df2 = pd.read_csv('/home/gmuser/esmm_data/native.csv')
+    df2['cid_id'] = df2['cid_id'].astype(str)
+
+    df1 = pd.read_csv("/home/gmuser/esmm_data/native/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    df2["ctr"],df2["cvr"],df2["ctcvr"] = df1["ctr"],df1["cvr"],df1["ctcvr"]
+    df3 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':native_set_join}).reset_index(drop=False)
+    df3.columns = ["device_id","city_id","native_queue"]
+    print("native_device_count",df3.shape)
+
+
+    # nearby queue
+    df2 = pd.read_csv('/home/gmuser/esmm_data/nearby.csv')
+    df2['cid_id'] = df2['cid_id'].astype(str)
+
+    df1 = pd.read_csv("/home/gmuser/esmm_data/nearby/pred.txt",sep='\t',header=None,names=["ctr","cvr","ctcvr"])
+    df2["ctr"], df2["cvr"], df2["ctcvr"] = df1["ctr"], df1["cvr"], df1["ctcvr"]
+    df4 = df2.groupby(by=["uid","city"]).apply(lambda x: x.sort_values(by="ctcvr",ascending=False)).reset_index(drop=True).groupby(by=["uid","city"]).agg({'cid_id':nearby_set_join}).reset_index(drop=False)
+    df4.columns = ["device_id","city_id","nearby_queue"]
+    print("nearby_device_count",df4.shape)
+
+    #union
+    df_all = pd.merge(df3,df4,on=['device_id','city_id'],how='outer').fillna("")
+    df_all['device_id'] = df_all['device_id'].astype(str)
+    df_all['city_id'] = df_all['city_id'].astype(str)
+    ctime = int(time.time())
+    df_all["time"] = ctime
+    print("union_device_count",df_all.shape)
+
+
+
+    host='10.66.157.22'
+    port=4000
+    user='root'
+    password='3SYz54LS9#^9sBvC'
+    db='jerry_test'
+    charset='utf8'
+
+    engine = create_engine(str(r"mysql+mysqldb://%s:" + '%s' + "@%s:%s/%s") % (user, password, host, port, db))
+
+    try:
+        # df_merge = df_all[['device_id','city_id']].apply(lambda x: ''.join(x),axis=1)
+        df_merge = df_all['device_id'] + df_all['city_id']
+        df_merge_str = (str(list(df_merge.values))).strip('[]')
+        delete_str = 'delete from esmm_device_diary_queue where concat(device_id,city_id) in ({0})'.format(df_merge_str)
+        con = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
+        cur = con.cursor()
+        cur.execute(delete_str)
+        con.commit()
+        df_all.to_sql('esmm_device_diary_queue',con=engine,if_exists='append',index=False)
+    except Exception as e:
+        print(e)
+
+
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file

tensnsorflow/es/to_tfrecord.py

+#coding=utf-8
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+import pandas as pd
+import sys
+import os
+import glob
+
+import tensorflow as tf
+import numpy as np
+import re
+from multiprocessing import Pool as ThreadPool
+
+flags = tf.app.flags
+FLAGS = flags.FLAGS
+LOG = tf.logging
+
+tf.app.flags.DEFINE_string("input_dir", "./", "input dir")
+tf.app.flags.DEFINE_string("output_dir", "./", "output dir")
+tf.app.flags.DEFINE_integer("threads", 16, "threads num")
+
+def gen_tfrecords(in_file):
+    basename = os.path.basename(in_file) + ".tfrecord"
+    out_file = os.path.join(FLAGS.output_dir, basename)
+    tfrecord_out = tf.python_io.TFRecordWriter(out_file)
+    df = pd.read_csv(in_file)
+
+    for i in range(df.shape[0]):
+        feats = ["ucity_id", "clevel1_id", "ccity_name", "device_type", "manufacturer",
+                "channel", "top", "l1", "time", "stat_date","l2"]
+        id = np.array([])
+        for j in feats:
+            id = np.append(id,df[j][i])
+        features = tf.train.Features(feature={
+            "y": tf.train.Feature(float_list=tf.train.FloatList(value=[df["y"][i]])),
+            "z": tf.train.Feature(float_list=tf.train.FloatList(value=[df["z"][i]])),
+            "ids": tf.train.Feature(int64_list=tf.train.Int64List(value=id.astype(np.int)))
+        })
+
+        example = tf.train.Example(features = features)
+        serialized = example.SerializeToString()
+        tfrecord_out.write(serialized)
+    tfrecord_out.close()
+
+def main(_):
+    if not os.path.exists(FLAGS.output_dir):
+        os.mkdir(FLAGS.output_dir)
+    file_list = glob.glob(os.path.join(FLAGS.input_dir, "*.csv"))
+    print("total files: %d" % len(file_list))
+
+    pool = ThreadPool(FLAGS.threads) # Sets the pool size
+    pool.map(gen_tfrecords, file_list)
+    pool.close()
+    pool.join()
+
+
+if __name__ == "__main__":
+    tf.logging.set_verbosity(tf.logging.INFO)
+    tf.app.run()
\ No newline at end of file

tensnsorflow/multi_hot.py

+import pandas as pd
+import pymysql
+import datetime
+from sqlalchemy import create_engine
+
+def con_sql(db,sql):
+    cursor = db.cursor()
+    try:
+        cursor.execute(sql)
+        result = cursor.fetchall()
+        df = pd.DataFrame(list(result))
+    except Exception:
+        print("发生异常", Exception)
+        df = pd.DataFrame()
+    finally:
+        db.close()
+    return df
+
+
+def multi():
+    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
+    sql = "select diary_id,level2_ids from diary_feat"
+    df = con_sql(db, sql).dropna()
+    print(df.shape)
+    df = df.rename(columns={0: "cid", 1: "level"})
+    df["l1"] = "lost"
+    df["l2"] = "lost"
+    df["l3"] = "lost"
+    for i in list(df["level"].unique()):
+        l = [int(j) for j in i.split(";")]
+        l = sorted(l)
+        if len(l) >= 3:
+            df.loc[df["level"] == i, ["l1"]] = l[0]
+            df.loc[df["level"] == i, ["l2"]] = l[1]
+            df.loc[df["level"] == i, ["l3"]] = l[2]
+        elif len(l) == 2:
+            df.loc[df["level"] == i, ["l1"]] = l[0]
+            df.loc[df["level"] == i, ["l2"]] = l[1]
+        elif len(l) == 1:
+            df.loc[df["level"] == i, ["l1"]] = l[0]
+    df = df.drop("level",axis=1)
+    print(df.head())
+    # a = list(df["l1"].unique())
+    # b = list(df["l2"].unique())
+    # c = list(df["l3"].unique())
+    # print(len(a))
+    # print(a)
+    # print(len(b))
+    # print(b)
+    # print(len(c))
+    # print(c)
+
+    yconnect = create_engine('mysql+pymysql://root:3SYz54LS9#^9sBvC@10.66.157.22:4000/jerry_test?charset=utf8')
+    n = 200000
+    for i in range(0, df.shape[0], n):
+        if i == 0:
+            temp = df.iloc[0:n]
+        elif i + n > df.shape[0]:
+            temp = df.iloc[i:]
+        else:
+            temp = df.iloc[i:i + n]
+        pd.io.sql.to_sql(temp, "cid_level2", yconnect, schema='jerry_test', if_exists='append', index=False)
+        print("insert done")
+
+
+
+if __name__ == "__main__":
+    multi()
\ No newline at end of file

tensnsorflow/test.py

-import pandas as pd
-import pymysql
-
-
-def con_sql(db,sql):
-    cursor = db.cursor()
-    try:
-        cursor.execute(sql)
-        result = cursor.fetchall()
-        df = pd.DataFrame(list(result))
-    except Exception:
-        print("发生异常", Exception)
-        df = pd.DataFrame()
-    finally:
-        db.close()
-    return df
-
-
-
-def exp():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select native_queue from esmm_device_diary_queue where device_id = '358035085192742'"
-    cursor = db.cursor()
-    cursor.execute(sql)
-    result = cursor.fetchone()[0]
-    native = tuple(result.split(","))
-    print("total")
-    print(len(native))
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
-    sql = "select diary_id,level1_ids,level2_ids,level3_ids from diary_feat where diary_id in {}".format(native)
-    df = con_sql(db,sql)
-
-    n = df.shape[0]
-    one = df[1].unique()
-    one_map = {}
-    for i in one:
-        one_map[i] = df.loc[df[1]==i].shape[0]/n
-    print(sorted(one_map.items(),key = lambda x:x[1]))
-    two = df[2].unique()
-    two_map = {}
-    print("分界线")
-    for i in two:
-        two_map[i] = df.loc[df[2] == i].shape[0] / n
-    print(sorted(two_map.items(), key=lambda x: x[1]))
-
-
-def click():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_prod')
-    sql = "select d.cid_id,f.level1_ids,f.level2_ids from data_feed_click d left join diary_feat f " \
-          "on d.cid_id = f.diary_id where d.device_id = '358035085192742' " \
-          "and (d.cid_type = 'diary' or d.cid_type = 'diary_video') and d.stat_date > '2018-12-20'"
-    df = con_sql(db, sql)
-
-    n = df.shape[0]
-    print(n)
-    one = df[1].unique()
-    one_map = {}
-    for i in one:
-        one_map[i] = df.loc[df[1] == i].shape[0] / n
-    print(sorted(one_map.items(), key=lambda x: x[1],reverse=True))
-    two = df[2].unique()
-    two_map = {}
-    print("分界线")
-    for i in two:
-        two_map[i] = df.loc[df[2] == i].shape[0] / n
-    print(sorted(two_map.items(), key=lambda x: x[1],reverse=True))
-
-def get_cid():
-    db = pymysql.connect(host='10.66.157.22', port=4000, user='root', passwd='3SYz54LS9#^9sBvC', db='jerry_test')
-    sql = "select cid_id from esmm_train_data where device_id = '358035085192742' " \
-          "and stat_date >= '2018-12-03'"
-    df = con_sql(db, sql)[0].values.tolist()
-    print(",".join(df))
-
-
-
-if __name__ == "__main__":
-
-    import pandas as pd
-    from sklearn.preprocessing import MinMaxScaler
-
-
-    # 读取葡萄酒数据集
-    data = pd.read_csv("G:/dataset/wine.csv")
-    # 获取第二列Alcohol
-    x = data["Alcohol"]
-    # 获取数据的基本情况
-    print(x.describe())
-    minMax = MinMaxScaler()
-    # 将数据进行归一化
-    x_std = minMax.fit_transform(x)
-    pd.DataFrame()
-
-