def getStore(uuid):
store = json.load(open("raw_data/raw_" + uuid + ".txt"))['data']
if store.get("code") == 500:
print("Error: ", uuid)
return
if not store.get("location"):
print("Error Address: ", uuid)
return
code = store["location"].get("postalCode")
if not code or len(str(code)) < 3:
loc = store.get("location").get("address")
code = zipcodetw.find(loc)
if not code or len(str(code)) < 3:
loc_strip = re_word.findall(loc)[0]
loc_strip = loc_strip.replace("台灣", "")
code = zipcodetw.find(loc_strip)
if not code or len(str(code)) < 3:
code = re_word_code.findall(loc)
if len(code):
code = code[0]
if code and len(str(code)) < 3:
print("Error postcode digit: ", code, loc, uuid)
return
if not code:
print("Error postcode: ", loc, uuid)
return
code = int(str(code)[:3])
# debug
# return
rate = 0
rate_num = 0
if store["ratingBadge"]:
rate = store["ratingBadge"][0]["children"][0]["text"]
rate_num = re.findall(r"\d+", store["ratingBadge"][0]["children"][2]["text"])[0]
# print("Error rate: ", uuid)
if len(store["categories"]) != 2:
print("Error categories number: ", uuid)
return
prices = [j["price"] for _, i in store["sectionEntitiesMap"].items() for _, j in i.items()]
try:
now_dict = {
"uuid": uuid,
"city": store["citySlug"],
"postcode": code,
"rate": rate,
"rate_num": rate_num,
"food_num": len(prices),
"food_mean": np.mean(prices),
"food_q1": np.quantile(prices, 0.25),
"food_q2": np.quantile(prices, 0.50),
"food_q3": np.quantile(prices, 0.75),
"food_var": np.std(prices),
"category": store["categories"][1],
"money": store["categories"][0],
}
except:
pprint(store)
raise
all_stores.append(now_dict)
def FillACPAAA016(df):
#print(df["郵遞區號"])
indexcol = int(df.columns.get_loc("郵遞區號"))
for index,row in df.iterrows():
if (row.郵遞區號 == '' or row.郵遞區號 == None):
df.iloc[index,indexcol] = str(zipcodetw.find(row.地址))
return df
def updateZipCode(self, text):
code = zipcodetw.find(text)
self.oField.setText(' '.join([code, text]))
def test_find():
zipcodetw.find('台北市')
zipcodetw.find('台北市中正區')
zipcodetw.find('台北市中正區仁愛路')
zipcodetw.find('台北市中正區仁愛路2段')
zipcodetw.find('台北市中正區仁愛路2段45號')
zipcodetw.find('台中市')
zipcodetw.find('台中市中區')
zipcodetw.find('台中市中區台灣大道')
zipcodetw.find('台中市中區台灣大道1段')
zipcodetw.find('台中市中區台灣大道1段239號')
zipcodetw.find('臺南市')
zipcodetw.find('臺南市中西區')
zipcodetw.find('臺南市中西區府前路')
zipcodetw.find('臺南市中西區府前路1段')
zipcodetw.find('臺南市中西區府前路1段226號')
def api_find():
return jsonify(result=zipcodetw.find(request.values.get('address')))
def api_find():
return jsonify(result=zipcodetw.find(request.values.get('address')))
import pandas as pd
import zipcodetw
# make sure python3 -m zipcodetw.builder
postcode = pd.read_csv("data/postcode.csv")
data = pd.read_csv("download/NPA_TMA2.csv")
data.insert(2, "postcode", -1, True)
for i in range(len(data)):
print(i)
loc = data.iloc[i]["發生地點"]
if pd.isna(loc):
continue
code = zipcodetw.find(loc)
code = code[:3]
if 100 <= int(code) < 200:
data.at[i, "postcode"] = int(code)
data = data[data["postcode"] != -1]
data.to_csv("data/crash.csv", index=False)
print(data)
new_data = []
data = pd.read_csv("data/crash.csv")
codes = set(data["postcode"])
for code in codes:
if code >= 200 or code < 100:
continue
new_data.append({"postcode": code, "num": sum(data["postcode"] == code)})
new_data = pd.DataFrame(new_data)
new_data.to_csv("data/crash_num.csv", index=False)
def test_find():
zipcodetw.find('台北市')
zipcodetw.find('台北市中正區')
zipcodetw.find('台北市中正區仁愛路')
zipcodetw.find('台北市中正區仁愛路2段')
zipcodetw.find('台北市中正區仁愛路2段45號')
zipcodetw.find('台中市')
zipcodetw.find('台中市中區')
zipcodetw.find('台中市中區台灣大道')
zipcodetw.find('台中市中區台灣大道1段')
zipcodetw.find('台中市中區台灣大道1段239號')
zipcodetw.find('臺南市')
zipcodetw.find('臺南市中西區')
zipcodetw.find('臺南市中西區府前路')
zipcodetw.find('臺南市中西區府前路1段')
zipcodetw.find('臺南市中西區府前路1段226號')
def main():
return zipcodetw.find(sys.argv[1])
