def cal(self):
origin = load("info")
df = origin.drop_duplicates(["brand", "model", "tag"])
df = df.groupby(["tag"]).apply(self.cal_aver_top)
df = df.drop_duplicates(
["tag"])[["tag", "top_tag", "aver_model_tag_ratings"]]
dump(pd.merge(origin, df, "left", on=["tag"]), "info")
def trans(self):
df = load("info")
df['target_score'] = df['target_score'].str.replace('\'"', '"')
df['target_score'] = df['target_score'].str.replace('"\'', '"')
df['target_score'] = df['target_score'].str.replace('\'', '')
df['target_score'] = df['target_score'].str.replace('\\', '')
df['model_target_ratings'] = df['model_target_ratings'].str.replace('\'"', '"')
df['model_target_ratings'] = df['model_target_ratings'].str.replace('"\'', '"')
df['model_target_ratings'] = df['model_target_ratings'].str.replace('\'', '')
df['model_target_ratings'] = df['model_target_ratings'].str.replace('\\', '')
df['model_target_rank'] = df['model_target_rank'].str.replace('\'"', '"')
df['model_target_rank'] = df['model_target_rank'].str.replace('"\'', '"')
df['model_target_rank'] = df['model_target_rank'].str.replace('\'', '')
df['model_target_rank'] = df['model_target_rank'].str.replace('\\', '')
df['aver_model_target_ratings'] = df['aver_model_target_ratings'].str.replace('\'"', '"')
df['aver_model_target_ratings'] = df['aver_model_target_ratings'].str.replace('"\'', '"')
df['aver_model_target_ratings'] = df['aver_model_target_ratings'].str.replace('\'', '')
df['aver_model_target_ratings'] = df['aver_model_target_ratings'].str.replace('\\', '')
df['top_target'] = df['top_target'].str.replace('\'"', '"')
df['top_target'] = df['top_target'].str.replace('"\'', '"')
df['top_target'] = df['top_target'].str.replace('\'', '')
df['top_target'] = df['top_target'].str.replace('\\', '')
def rank(self):
origin = load("info")
df = origin[["brand", "model",
"model_wilson"]].drop_duplicates(["brand", "model"])
df = self.rank_func(df, "model_wilson", "model_rank")
del df["model_wilson"]
dump(pd.merge(origin, df, "left", on=["brand", "model"]), "info")
def evaluate(self):
origin = load("info")
df = origin.drop_duplicates(["brand", "model"])
for k, v in df.iterrows():
df.at[k, "model_wilson"] = self.evaluate_score(
v["model_n"], v["model_p"], self.z)
df = df[["brand", "model", "model_wilson"]]
dump(pd.merge(origin, df, "left", on=["brand", "model"]), "info")
def rank(self):
origin = load("info")
df = origin[["brand", "model", "tag",
"tag_wilson"]].drop_duplicates(["brand", "model", "tag"])
df = df.groupby(["tag"]).apply(self.rank_func, "tag_wilson",
"model_tag_rank")
del df["tag_wilson"]
dump(pd.merge(origin, df, "left", on=["brand", "model", "tag"]),
"info")
def cal(self):
origin = load("info")
df = origin.drop_duplicates(["brand", "model", "tag"])[
["brand", "model", "tag_u", "tag_v"]]
df = df.groupby(["brand", "model"]).apply(
self.cal_baseline)
del df["tag_u"], df["tag_v"]
df = df.drop_duplicates(["brand", "model"])
dump(pd.merge(origin, df, "left", on=["brand", "model"]), "info")
def rank(self):
origin = load("info")
df = origin[["brand", "model", "tag", "target", "target_score"]]
df = df.groupby(["target"]).apply(self.rank_func, "target_score",
"model_target_rank")
del df["target_score"]
dump(
pd.merge(origin,
df,
"left",
on=["brand", "model", "tag", "target"]), "info")
def adjust(self):
df = load("info")
self.make_record(datamonths=set(df["datamonth"].values))
self.publish = min(self.record.values())
for k, v in df.iterrows():
df.at[k, "frequency"] = v["frequency"] * math.e**(
(self.record[v["datamonth"]] - self.publish) /
(self.current - self.publish))
# df.at[k, "frequency"] = v["frequency"] * (
# (self.record[v["datamonth"]] - self.publish) / (self.current - self.publish))
del df["datamonth"]
dump(df, "info")
def select(self):
df = load("info")
dump(df, "wholeInfo")
df = df[[
"brand", "model", "tag", "target", "model_score", "tag_score",
"target_score", "model_ratings", "model_tag_ratings",
"model_target_ratings", "model_rank", "model_tag_rank",
"model_target_rank", "aver_model_ratings",
"aver_model_tag_ratings", "aver_model_target_ratings", "top_model",
"top_tag", "top_target"
]]
dump(df, "info")
def cal(self):
df = load("info")
for inx, row in df.iterrows():
if 1 == row["grade"]:
df.at[inx, "u"] = row["frequency"]
df.at[inx, "v"] = 0
elif -1 == row["grade"]:
df.at[inx, "u"] = 0
df.at[inx, "v"] = row["frequency"]
del df["frequency"], df["grade"]
df = df.groupby(["brand", "model", "tag", "target"]).apply(
self.cal_baseline)
del df["u"], df["v"]
df = df.drop_duplicates(["brand", "model", "tag", "target"])
dump(df, "info")
def evaluate(self):
df = load("info")
for k, v in df.iterrows():
df.at[k, "target_wilson"] = self.evaluate_score(
v["target_n"], v["target_p"], self.z)
dump(df, "info")
def adjust(self):
df = load("info")
del df["datamonth"]
dump(df, "info")
def trans(self):
df = load("info")
df = df.groupby(["brand", "model"]).apply(self.trans_func)
del df["tag"]
df = df.drop_duplicates(["brand", "model"])
dump(df, "info")
def cal(self):
df = load("info")
df = df.groupby(["tag", "target"]).apply(self.cal_aver_top)
dump(df, "info")
def cal(self):
origin = load("info")
df = origin.drop_duplicates(["brand", "model"])
top, aver = self.cal_aver_top(df)
origin["top_model"], origin["aver_model_ratings"] = top, aver
dump(origin, "info")
def cal(self):
df = load("info")[["tag", "tag_score", "tag_u", "tag_v", "tag_n"]]
df = df.groupby(['tag']).apply(self.aspect_info)
self.make_info(df)
def cal(self):
df = load("info")[[
"brand", "model", "model_score", "model_u", "model_v", "model_n"
]]
df = self.aspect_info(df)
self.make_info(df)
def cal(self):
df = load("info")[[
"tag", "target", "target_score", "target_u", "target_v", "target_n"
]]
df = df.groupby(["tag", "target"]).apply(self.aspect_info)
self.make_info(df)
def cal(self):
df = load("info")
df = df.groupby(["brand", "model", "tag"]).apply(
self.cal_baseline)
dump(df, "info")
