import tpot
from tpot import TPOTClassifier
from sklearn.metrics import precision_score, f1_score, recall_score
import warnings
import numpy as np
import pandas as pd
import pymysql
from collections import Counter
if __name__ == '__main__':
warnings.filterwarnings('ignore')
from sklearn.metrics import precision_score, f1_score, recall_score
warnings.filterwarnings('ignore')
# 加载数据
sql = "SELECT * from bidata.trail_pigeon_wdf1"
df = load_data_new(sql, filename="drumping.csv")
df_btest = load_data_new(sql, filename="btest.csv")
label_by_contract = "target_is_DD_ACTIVE"
labels = label_by_contract
select_columns = [
"CAFE20_gender",
"CAFE20_region",
"CAFE20_levels",
"is_festival_user",
"level_use",
"is_LAST_2YEAR_DD_ACTIVE",
"cafe_tag_is_mop_available",
"is_merch_user",
"p4week_active",
from model_evalu import evalution_model, plot_importance
import numpy as np
from models import rf_mdoel, gbdt_mdoel, xgb_model, cat_boost_model
from sklearn.metrics import make_scorer
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from xgboost import XGBClassifier
from sklearn.metrics import precision_score, f1_score, recall_score
from sklearn.base import clone
if __name__ == '__main__':
warnings.filterwarnings('ignore')
from sklearn.metrics import precision_score, f1_score, recall_score
warnings.filterwarnings('ignore')
# 加载数据
sql = "SELECT * from bidata.trail_pigeon_wdf1"
df = load_data_new(sql, filename="drumping.csv")
label_by_contract = "target_is_DD_ACTIVE"
labels = label_by_contract
select_columns = [
"CAFE20_gender",
"CAFE20_region",
"CAFE20_levels",
"is_festival_user",
"level_use",
"is_LAST_2YEAR_DD_ACTIVE",
"cafe_tag_is_mop_available",
"is_merch_user",
"p4week_active",
"is_LAST_1YEAR_DD_ACTIVE",
from data_treatment import data_clean2
from data_treatment import load_data_new
import joblib
import pandas as pd
import matplotlib.pyplot as plt
if __name__ == '__main__':
sql = " "
df = load_data_new(sql, filename="btest.csv")
df = data_clean2(df)
labels = "target_is_DD_ACTIVE"
select_columns = [
'is_festival_user',
'is_LAST_2YEAR_DD_ACTIVE',
'cafe_tag_is_mop_available',
'IS_SR_KIT_USER',
'level_use',
'skr_rate',
'merch_rate',
'active_index',
'cafe_tag_p6m_food_qty',
'DD_rev',
'svc_revenue',
'SR_KIT_NUM',
'cafe_tag_p3m_merch_party_size',
'CAFE20_VISIT_MERCH',
'CAFE20_AMT',
'cafe_tag_p3m_food_qty',
'p3m_weekday_trans',
'max_DD_rev',
'DD_end_gap',
import tpot
from tpot import TPOTClassifier
from sklearn.metrics import precision_score, f1_score, recall_score
import warnings
import numpy as np
import pandas as pd
import pymysql
from collections import Counter
if __name__ == '__main__':
warnings.filterwarnings('ignore')
from sklearn.metrics import precision_score, f1_score, recall_score
warnings.filterwarnings('ignore')
# 加载数据
sql = "SELECT * from bidata.trail_pigeon_wdf1"
df = load_data_new(sql, filename="df_20190226.csv")
label_by_contract = "is_pigeon"
labels = label_by_contract
select_columns = [
# "sale_id",
# "teacher_id",
"know_origin",
"grade_subject",
"student_city_class",
"student_province",
"grade_rank",
"class_rank_fillna",
"student_province_byphone",
"subject_ids",
from model_evalu import evalution_model
if __name__ == '__main__':
labels = "attend"
file = "load_data/audio_data_with_success_attend_cutwords.pkl"
with open(file, 'rb') as f:
data = pickle.load(f)
#student_intention_id
sql_student = """SELECT v.student_id,v.student_intention_id,v.student_no,lpo.apply_time AS order_apply_time,lpo.order_id ,v.submit_time from hfjydb.view_student v
LEFT JOIN hfjydb.lesson_plan_order lpo on lpo.student_intention_id = v.student_intention_id"""
df_student = load_data_new(sql_student, filename="df_students_s.csv")
df_student = df_student[~df_student["order_id"].isnull()]
df_concat = pd.merge(data, df_student, on="student_intention_id", how="left")
df_concat = df_concat[~df_concat["order_id"].isnull()]
conts = df_concat["student_intention_id"].value_counts()
conts = conts[conts == 1]
df_concat = df_concat[df_concat["student_intention_id"].isin(list(conts.index))]
df_voice = df_concat[["order_id", "order_apply_time", "attend", "content"]]
print(1)
#分词
start = time.clock()
import warnings
warnings.filterwarnings('ignore')
from data_treatment import load_data_new, data_clean2
import pandas as pd
from statsmodels.formula.api import ols
from statsmodels.stats.anova import anova_lm
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
if __name__ == '__main__':
sql = "select * from bidata.trail_pigeon"
df = load_data_new(sql, filename="df_20190215.csv")
student_sql = """SELECT student_id,count(student_id) from trail_pigeon
GROUP BY student_id"""
student_mul = load_data_new(student_sql, filename="student_mul.csv")
student_ids = student_mul[student_mul["count(student_id)"] == 1]
df = df[df["student_id"].isin(student_mul["student_id"])]
label_by_contract = "is_pigeon"
labels = label_by_contract
# 数据预处理
df = data_clean2(df,
min_date="2018-05-01",
mid_date="2018-09-15",
max_date="2018-09-30",
label=labels)
from sklearn.metrics import make_scorer
from sklearn.ensemble import RandomForestClassifier,GradientBoostingClassifier
from model_evalu import evalution_model,plot_importance
import numpy as npr
from xgboost import XGBClassifier
from sklearn.metrics import precision_score,f1_score,recall_score
import warnings
import pandas as pd
import numpy as np
import pymysql
from catboost import CatBoostClassifier,CatBoostRegressor,Pool
if __name__ == '__main__':
warnings.filterwarnings('ignore')
#加载数据
sql = "select * from bidata.trail_boost"
df = load_data_new(sql, filename="df_201810166.csv")
#加载新数据
# sql_new = "select DISTINCT teacher_id,history_trail_cnt,history_trail_suc_cnt_bycontract,history_trail_suc_cnt_bystudent,first_tkod_tifl_count from trail_boost"
# conn = pymysql.connect(host="rm-2ze974348wa9e1ev3uo.mysql.rds.aliyuncs.com", port=3306, user="******",
# passwd="xMbquuHi98JyfiF1", db="bidata", charset="utf8")
# df_new = pd.read_sql(sql_new, conn)
# conn.close()
#
# df = pd.merge(df,df_new,how="left",on=["teacher_id"])
label_by_contract = "is_sucess_by_contract"
label_by_pay = "is_sucess_by_pay"
label_by_official_course = "is_sucess_by_official_course"
labels = label_by_contract
select_columns = [