def login_and_getdata():
print('获取cookis...')
try:
s.cookies = get_cookie_from_file()
except:
print("从文件获取cookies失败...\n正在尝试提交表单登录以获取...")
s.cookies = get_cookie_from_net()
# 开始爬取数据
get_all_data(s, headers)
def forecast_regression(dt, car_park):
"""Regression-based forecast of time series."""
# get training data (for 'car_park')
df = get_data.get_all_data()
# build X and y for model fitting
# TODO
# train random forest model
rf = RandomForestRegressor()
def forecast_linear(dt, car_park):
"""Simple linear prediction."""
# get latest two observations, before the given point in time
df = get_data.get_all_data()
df2 = df[(df.datetime < str(dt)) & (df.name == car_park)]
df3 = df2.sort_values(by='datetime')
df4 = df3.tail(n=2)
second_latest = df4.head(n=1)
latest = df4.tail(n=1)
# calculate delta for capacity (per second)
diff_time = (latest.datetime.iloc[0] - second_latest.datetime.iloc[0])
diff_sec = diff_time.seconds
diff_cap = (latest.cap.iloc[0] - second_latest.cap.iloc[0])
d_cap_per_sec = diff_cap / diff_sec
# linearly extrapolate to the requested point in time
fcst_sec = (dt - latest.datetime.iloc[0]).seconds
fcst_cap = latest.cap.iloc[0] + d_cap_per_sec * fcst_sec
# limit prediction to min-max range of all observations for this car-park
fcst_cap = max(fcst_cap, 0)
return (fcst_cap)
import get_data as gd
'''取json檔所有資料
get_all_data("面積.json") 取面積資料
get_all_data("人口結構.json") 取人口結構資料
get_all_data("所得.json") 取所得資料
get_all_data("性別.json") 取性別資料
get_all_data("社會增加.json") 取社會增加資料
get_all_data("教育程度.json") 取教育程度資料
'''
d = gd.get_all_data("面積.json")
#取單一里資料
d_a = gd.get_data_by_neighborhood("性別.json", "頂寮里")
print(d)
print(d_a)
def load_ema_data(self, path):
self.emas = get_all_data(path, 'ema')
def load_lsf_data(self, path):
self.lsfs = get_all_data(path, 'lsf')
os.makedirs(OUT_PARENT_DIR)
outf_path = '%s/%s' % (OUT_PARENT_DIR, 'fr%s.csv' % curr_gw)
with open(outf_path, 'w', encoding='utf8') as outf:
wrtr = csv.DictWriter(outf, hdrs)
wrtr.writeheader()
if curr_gw: # natural_number -> 0-index
curr_gw -= 1
rfs = gen_ranked_fixtures(tfd, curr_gw, n_avgs, look_ahead)
rfd = [dict(zip(hdrs, rf)) for rf in rfs]
# presorted_rfs = sorted(rfd, key=lambda rf: float(rf[T0AVG])) # sort by diff
presorted_rfs = sorted(rfd, key=lambda rf: rf['team'])
wrtr.writerows(presorted_rfs)
# truncate final new-line to facilitate auto-csv-rendering in Github
outf.truncate(outf.tell() - len(os.linesep) * 2)
if __name__ == '__main__':
get_data.get_all_data()
N_AVGS = 3
LOOK_AHEAD = 4
td = gen_teams()
tfd = gen_team_fixture(td)
# manual update eg for double-gameweeks
if update_team2fixts:
tfd = update_fixture(tfd, gameweek)
write_fixture_ranks(tfd, gameweek, N_AVGS, LOOK_AHEAD)
import get_data as gd
result = input()
result = open(result, "w", encoding="utf8")
d_soc_inc = gd.get_all_data("社會增加.json")
list_dist = ["下寮里", "大村里", "大庄里", "中正里", "中和里", "文化里",
"永安里", "永寧里", "安仁里", "南簡里", "草湳里", "頂寮里", "福德里", "興農里"]
list_rate = []
for dist in list_dist:
rate = d_soc_inc[dist][3]
list_rate.append((dist, rate))
list_rate = sorted(list_rate, key=lambda x: (float(x[1]), x[0]), reverse=True)
rresult = []
rate_low = float(list_rate[13][1])
rate_adj = 10/(float(list_rate[0][1])-rate_low)
for i in range(14):
dist = list_rate[i][0]
rate = float(list_rate[i][1])
if i == 0:
com = [dist, 10]
elif i == 13:
com = [dist, 0]
elif rate < 0:
com = [dist, 0]
else:
score = (float(rate)-rate_low)*rate_adj
com = [dist, score]
rresult.append(com)
result.writelines("梧棲區社會增加率分數\n")
result.writelines("\n")
for com in rresult:
"""Plot target variable as time series."""
import get_data
from ggplot import aes, geom_line, facet_wrap, ggplot
if __name__ == "__main__":
df = get_data.get_all_data()
p = ggplot(df, aes('datetime', 'cap', group='date')) + \
geom_line(alpha=0.2) + \
facet_wrap('name')
p.save('../output/time_series.pdf')
import get_data as gd
d_humcom = gd.get_all_data("人口結構.json")
print(d_humcom)
from sklearn.compose import make_column_transformer
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder
from get_data import get_all_data
# scikitlearn tip #1
df = get_all_data()
df.head()
ohe = OneHotEncoder()
imp = SimpleImputer()
ct = make_column_transformer((ohe, ['imS']), (imp, ['imL']),
remainder='passthrough')
new_matrix = ct.fit_transform(df)
# scikitlearn tip #2
ct2 = make_column_transformer((ohe, ['imS']))
new_matyrix_2 = ct2.fit_transform(df)
new_matyrix_2.shape
import get_data as gd
d_square = gd.get_all_data("面積.json")
list_dist = ["下寮里", "大村里", "大庄里", "中正里", "中和里", "文化里",
"永安里", "永寧里", "安仁里", "南簡里", "草湳里", "頂寮里", "福德里", "興農里"]
list_square = []
for dist in list_dist:
list_square.append(dist, d_square[dist][1])
people_com = input()
result = input()
people_com = open(people_com, "r", encoding="utf8")
result = open(result, "a", encoding="utf8")
Funder18 = dict()
F19to35 = dict()
F36to45 = dict()
Fotherage = dict()
Munder18 = dict()
M19to35 = dict()
M36to45 = dict()
Motherage = dict()
list_1part = []
list_allpart = []
for line in people_com:
line = line.strip(" ")
line = line.replace('"', "")
line = line.strip("\n")
line = line.strip(",")
if line != "{" and line != "[" and line != "]" and line != "}":
if "總計" not in line:
cut = line.find(":")
line = line[cut+2:len(line)]
import get_data as gd
result = input()
result = open(result, "w", encoding="utf8")
d_gender = gd.get_all_data("性別.json")
d_square = gd.get_all_data("面積.json")
list_dist = [
"下寮里", "大村里", "大庄里", "中正里", "中和里", "文化里", "永安里", "永寧里", "安仁里", "南簡里",
"草湳里", "頂寮里", "福德里", "興農里"
]
list_male = []
list_female = []
print(d_square)
for dist in list_dist:
male = d_gender[dist][1]
female = d_gender[dist][2]
sqaure = float(d_square[dist])
mcom = (dist, male / sqaure)
fcom = (dist, female / sqaure)
list_male.append(mcom)
list_female.append(fcom)
list_male = sorted(list_male, key=lambda x: (x[1], x[0]), reverse=True)
list_female = sorted(list_female, key=lambda x: (x[1], x[0]), reverse=True)
print(list_male)
male_low = float(list_male[13][1])
female_low = float(list_female[13][1])
male_adj = 10 / (float(list_male[0][1]) - male_low)
female_adj = 10 / (float(list_female[0][1]) - female_low)
print(male_adj, "male_adj")
mresult = []
fresult = []
import get_data as gd
result = input()
result = open(result, "w", encoding="utf8")
d_educ = gd.get_all_data("教育程度.json")
d_square = {
"下寮里": 0.3275,
"大村里": 1.3775,
"大庄里": 1.4125,
"中正里": 0.2100,
"中和里": 0.0954,
"文化里": 0.1925,
"永安里": 1.6575,
"永寧里": 1.6275,
"安仁里": 0.1325,
"南簡里": 1.8750,
"草湳里": 3.3175,
"頂寮里": 0.8675,
"福德里": 1.4995,
"興農里": 2.0125
}
list_dist = [
"下寮里", "大村里", "大庄里", "中正里", "中和里", "文化里", "永安里", "永寧里", "安仁里", "南簡里",
"草湳里", "頂寮里", "福德里", "興農里"
]
d_a = gd.get_data_by_neighborhood("面積.json", "面積")
list_gra = []
list_college = []
list_high = []