def build(self):
items = read("factItem")()
items = items[items["brand"] == items["brand"]]
macro_condition = load("statsAllSubMacroCondition")
def sum_sold(df):
sold_sum = df["total_sold_price"].sum()
df["sold_sum"] = sold_sum
try:
df["sold_share"] = sold_sum / macro_condition["total"]
except ZeroDivisionError:
df["sold_share"] = 0
return df
items["total_sold_price"] = items["total_sold_price"].fillna(0)
items = items.groupby(["brand"]).apply(sum_sold).drop_duplicates(
["brand"]).sort_values("sold_sum", ascending=False)
items = items[["brand", "sold_sum", "sold_share"]]
prev, rank = 0, 0
for k, v in items.iterrows():
if prev != v["sold_sum"]:
rank += 1
prev = v["sold_sum"]
items.at[k, "rank"] = rank
super().dump(items, "statsTopSoldBrands")
def cut(self):
df = read("factItem")()
title = "".join(list(df['title']))
cut_word = jieba.analyse.textrank(title, topK=self.threshold["title"])
title_words = set()
for i, word in enumerate(list(cut_word)):
title_words.add(word)
dump(title_words, "titleHotWords")
df = read("hotWords")()
title = "".join(list(df['hotwords']))
cut_word = jieba.analyse.textrank(title,
topK=self.threshold["hot search"])
search_words = set()
for i, word in enumerate(list(cut_word)):
search_words.add(word)
dump(search_words, "searchHotWords")
def statistic(self):
if Mode.statsLOCAL:
try:
load("statsTopSoldBrand")
except FileNotFoundError:
print(
"StatisticTopSoldBrandMethod: Don't Have Local Result Files"
)
else:
return
items = read("factItem")()
items = items[items["brand"] == items["brand"]]
macro_condition = load("statsAllSubMacroCondition")
def sum_sold(df):
sold_sum = df["total_sold_price"].sum()
df["sold_sum"] = sold_sum
try:
df["sold_share"] = sold_sum / macro_condition["total"]
except ZeroDivisionError:
df["sold_share"] = 0
return df
items["total_sold_price"] = items["total_sold_price"].fillna(0)
items = items.groupby(["brand"]).apply(sum_sold).drop_duplicates(
["brand"]).sort_values("sold_sum", ascending=False)
items = items[["brand", "sold_sum", "sold_share"]]
prev, rank = 0, 0
for k, v in items.iterrows():
if prev != v["sold_sum"]:
rank += 1
prev = v["sold_sum"]
items.at[k, "rank"] = rank
dump(items, "statsTopSoldBrands")
def statistic(self):
if Mode.statsLOCAL:
try:
load("statsAllSubItemidSet")
load("statsAllSubBrandSet")
load("statsAllSubSellerSet")
load("statsAllSubBiz30day")
load("statsAllSubTotalSoldPrice")
load("statsAllSubSoldAverPrice")
load("statsAllSubMacroCondition")
load("statsAllItemidMapping")
load("statsAllSubBiz30dayShare")
load("statsAllSubBiz30dayRank")
load("statsAllSubBiz30dayReRank")
load("statsAllSubTotalSoldPriceShare")
load("statsAllSubTotalSoldPriceRank")
load("statsAllSubTotalSoldPriceReRank")
except FileNotFoundError:
print(
"StatisticAllSubmarketMethod: Don't Have Local Result Files"
)
else:
return
words = load("submarketWords")
items = read("factItem")()
itemid_set = dict()
brand_set = dict()
seller_set = dict()
biz30day = {word: 0 for word in words}
total_sold_price = {word: 0 for word in words}
macro_conditions = dict()
macro_conditions["biz30day"] = 0
macro_conditions["total"] = 0
itemid_mapping = dict()
for k, v in items.iterrows():
if k % 100 == 0:
print("process", k, "/", len(items))
for word in words:
if word in v["title"]:
itemid_set.setdefault(word, set()).add(v["itemid"])
brand_set.setdefault(word, set()).add(v["brand"])
seller_set.setdefault(word, set()).add(v["sellernick"])
biz30day[word] += v["biz30day"]
total_sold_price[word] += v["total_sold_price"]
macro_conditions.setdefault("itemid", set()).add(v["itemid"])
macro_conditions.setdefault("brand", set()).add(v["brand"])
macro_conditions.setdefault("seller", set()).add(v["sellernick"])
macro_conditions["biz30day"] += v["biz30day"]
macro_conditions["total"] += v["total_sold_price"]
if v["itemid"] in itemid_mapping.keys():
print("Warning: Duplicate Itemid", v["itemid"])
itemid_mapping[v["itemid"]] = (v["brand"], v["biz30day"],
v["total_sold_price"])
sold_price_aver = dict()
for word in words:
try:
sold_price_aver[word] = \
round(total_sold_price[word] / biz30day[word], 2)
except ZeroDivisionError:
sold_price_aver[word] = 0
try:
macro_conditions["aver"] = \
round(macro_conditions["total"] / macro_conditions["biz30day"], 2)
except ZeroDivisionError:
macro_conditions["aver"] = 0
# itemid_set["macro conditions"] = macro_conditions["itemid"]
# brand_set["macro conditions"] = macro_conditions["brand"]
# seller_set["macro conditions"] = macro_conditions["seller"]
# biz30day["macro conditions"] = macro_conditions["biz30day"]
# total_sold_price["macro conditions"] = macro_conditions["total"]
# sold_price_aver["macro conditions"] = macro_conditions["aver"]
dump(itemid_set, "statsAllSubItemidSet")
dump(brand_set, "statsAllSubBrandSet")
dump(seller_set, "statsAllSubSellerSet")
dump(biz30day, "statsAllSubBiz30day")
dump(total_sold_price, "statsAllSubTotalSoldPrice")
dump(sold_price_aver, "statsAllSubSoldAverPrice")
dump(macro_conditions, "statsAllSubMacroCondition")
dump(itemid_mapping, "statsAllItemidMapping")
biz30day_share = dict()
biz30day_rank = dict()
biz30day_rerank = dict()
total_sold_price_share = dict()
total_sold_price_rank = dict()
total_sold_price_rerank = dict()
items = sorted(biz30day.items(), key=lambda x: x[1], reverse=True)
prev, rank = 0, 0
for key, value in items:
try:
biz30day_share[key] = value / macro_conditions["biz30day"]
except ZeroDivisionError:
biz30day_share[key] = 0
if prev != value:
rank += 1
prev = value
biz30day_rank[key] = rank
biz30day_rerank.setdefault(rank, list()).append(key)
items = sorted(total_sold_price.items(),
key=lambda x: x[1],
reverse=True)
prev, rank = 0, 0
for key, value in items:
try:
total_sold_price_share[key] = value / macro_conditions["total"]
except ZeroDivisionError:
total_sold_price_share[key] = 0
if prev != value:
rank += 1
prev = value
total_sold_price_rank[key] = rank
total_sold_price_rerank.setdefault(rank, list()).append(key)
dump(biz30day_share, "statsAllSubBiz30dayShare")
dump(biz30day_rank, "statsAllSubBiz30dayRank")
dump(biz30day_rerank, "statsAllSubBiz30dayReRank")
dump(total_sold_price_share, "statsAllSubTotalSoldPriceShare")
dump(total_sold_price_rank, "statsAllSubTotalSoldPriceRank")
dump(total_sold_price_rerank, "statsAllSubTotalSoldPriceReRank")