def getDataDrugPoor(path, tt):
data = spark.read.format('parquet').load(path)
# 处理甲类药,获得甲类药每年的开销以及每年使用的数量
data01 = data.select('PersonalType', 'DrugName', 'DT', 'Count', 'FeeSum',
'AllowedComp', 'CompRatio', 'CompRatio_Type')
# & (data01.CompRatio_Type == '{}'.format(tt))
data01 = data01.where((data01.PersonalType == '17') & (data01.DrugName != '0')) \
.withColumn("Count", data01.Count.cast(IntegerType())) \
.withColumn("FeeSum", data01.FeeSum.cast(IntegerType())) \
.withColumn("DrugName", CD.changeNameUDF(data01.DrugName))
# data01.show()
data01 = data01.drop('PersonalType', 'CompRatio_Type', 'CompRatio',
'AllowedComp')
data01_Fee = data01.drop("Count") \
.groupby("DrugName") \
.pivot("DT", ['2017', '2018', '2019']) \
.agg(F.sum('FeeSum')) \
.fillna(0)
data01_Fee = data01_Fee.orderBy(data01_Fee['2019'].desc())
data_fee = []
for i in data01_Fee.head(20):
dd = {'drugName': i['DrugName']}
tt = [i['2017'], i['2018'], i['2019']]
dd['drugFee'] = tt
data_fee.append(dd)
def getGrowthRate(path):
data = spark.read.format('parquet').load(path) \
.select("PersonalType", "DT", "DiseaseName")
data = data.withColumn("DiseaseName", CD.changeNameUDF(data.DiseaseName)) \
.where(data.DiseaseName != '0') \
.withColumn("DT", data.DT.cast(IntegerType()))
data_poor = data.where(data.PersonalType == "17").drop("PersonalType")
data_rich = data.where(data.PersonalType != "17").drop("PersonalType")
calGrowthRate(data_poor, 0)
calGrowthRate(data_rich, 1)
def startCategorizer():
result_list = ['emergent reader', 'other']
book_filename = raw_input('manuscript file name: ')
freq, avg_dis = CreateData.createData(book_filename)
X = zeros((1, 2))
X[0] = [freq, avg_dis]
#classify unknown data with our model
clf = joblib.load('model_svm.pkl')
result = clf.predict(X[0])
print 'the book category is: ', result_list[(int(result[0])) - 1]
def ShowCoords(img_file, coord_file):
IMG_DCT = "photos_used/"
img = Image.open(IMG_DCT + img_file)
draw = ImageDraw.Draw(img)
COORDS_DCT = "coords/"
coord_list = CreateData.LoadCoords(coord_file, COORDS_DCT)
for c in coord_list:
if c[2] == 1:
x = c[0]
y = c[1]
draw.line([(x - 4, y - 4), (x + 4, y + 4)], fill="green", width=2)
draw.line([(x - 4, y + 4), (x + 4, y - 4)], fill="green", width=2)
del draw
Image._show(img)
def getDiseaseNums(df, year, sex, personalType):
"""
数量, 年龄阶段, 数量*10, 病名, 年份
@param sex:
@param df: 待处理的dataframe
@param year: 年份
@return:
"""
temp = df.withColumn("DiseaseName", CD.changeNameUDF(df.DiseaseName)) \
.where(df.DiseaseName != '0')
data_man = temp.select("DiseaseName", "Age") \
.where(temp.Sex == "{}".format(sex))
data_man_collect = data_man.rdd.collect()
dict = [
{"age": "0-9", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "10-19", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "20-29", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "30-39", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "40-49", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "50-59", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "60-69", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "70-79", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "80-89", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "90以上", "DiseaseList": [], "DiseaseNumList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
]
tt = 0
for result in data_man_collect:
tt += 1
age = int(result['Age'] / 10)
if age > 9:
age = 9
DiseaseName = str(result['DiseaseName'])
if DiseaseName in dict[age]['DiseaseList']:
dict[age]['DiseaseNumList'][DiseaseName] += 1
else:
dict[age]['DiseaseList'].append(DiseaseName)
dict[age]['DiseaseNumList'][DiseaseName] = 1
for i in dict:
i['DiseaseNumList'] = sorted(i['DiseaseNumList'].items(), key=lambda d: d[1], reverse=True)
# mongodb(year, i['age'], personalType, sex)
for t in dict:
print(t)
saveMongodb(t)
def calDiseaseNums(df, year, sex, personalType):
# TotalFee RealComp SelfPay
temp = df.withColumn("SelfPay", df.SelfPay.cast(IntegerType())) \
.withColumn("Age", df.Age.cast(IntegerType())) \
.withColumn("DiseaseName", CD.changeNameUDF(df.DiseaseName)) \
.where(df.DiseaseName != '0') \
.fillna(0)
data_man = temp.select("DiseaseName", "Age", "SelfPay") \
.where(temp.Sex == "{}".format(sex)) \
.drop("Sex")
data_man_collect = data_man.rdd.collect()
dict = [
{"age": "0-9", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "10-19", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "20-29", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "30-39", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "40-49", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "50-59", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "60-69", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "70-79", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "80-89", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
{"age": "90以上", "DiseaseList": [], "DiseaseFeeList": {}, "DT": year, "Sex": sex, "PersonalType": personalType},
]
tt = 0
for result in data_man_collect:
print(result)
tt += 1
age = int(result['Age'] / 10)
if age > 9:
age = 9
DiseaseName = str(result['DiseaseName'])
if DiseaseName in dict[age]['DiseaseList']:
dict[age]['DiseaseFeeList'][DiseaseName] += int(result['SelfPay'])
else:
dict[age]['DiseaseList'].append(DiseaseName)
dict[age]['DiseaseFeeList'][DiseaseName] = int(result['SelfPay'])
for i in dict:
i['DiseaseFeeList'] = sorted(i['DiseaseFeeList'].items(), key=lambda d: d[1], reverse=True)
for i in dict:
print(i)
saveMongodb(i)
import csv
import CreateData
from Bechdel import Bechdel
data = CreateData.CreateData()
movie_list = data.create_movie()
params = []
with open("bechdel_test_data", 'a') as csvFile:
writer = csv.writer(csvFile)
for movie in movie_list:
tester = Bechdel(movie)
tester.run_bechdel_test()
params.append(movie.movie_name)
params.append(tester.test1)
params.append(tester.test2)
params.append(tester.test3)
params.append(tester.overall)
writer.writerow(params)
csvFile.close()
def openImage(coord_dct):
event2canvas = lambda e, c: (c.canvasx(e.x), c.canvasy(e.y))
if (True):
root = Tk()
# setting up a tkinter canvas with scrollbars
frame = Frame(root, bd=2, relief=SUNKEN)
frame.grid_rowconfigure(0, weight=1)
frame.grid_columnconfigure(0, weight=1)
xscroll = Scrollbar(frame, orient=HORIZONTAL)
xscroll.grid(row=1, column=0, sticky=E + W)
yscroll = Scrollbar(frame)
yscroll.grid(row=0, column=1, sticky=N + S)
canvas = Canvas(frame,
bd=0,
xscrollcommand=xscroll.set,
yscrollcommand=yscroll.set)
canvas.grid(row=0, column=0, sticky=N + S + E + W)
xscroll.config(command=canvas.xview)
yscroll.config(command=canvas.yview)
frame.pack(fill=BOTH, expand=1)
# adding the image
File = askopenfilename(parent=root,
initialdir="M:/",
title='Choose an image.')
print("opening %s" % File)
img = PhotoImage(file=File)
img2 = Image.open(File)
arr = np.array(img2)
# arr = arr.astype(int)
coords = []
print(arr.shape)
h, w = arr.shape[:2]
canvas.create_image(0, 0, image=img, anchor="nw")
canvas.config(scrollregion=canvas.bbox(ALL))
mark_size = 3
mark_width = 2
basename = os.path.basename(File)
coord_file = basename.replace("PICT", "coords").replace("png", "csv")
try:
coord_list = CreateData.LoadCoords(coord_file, coord_dct)
for c in coord_list:
x = c[0]
y = c[1]
if c[2] == 1:
canvas.create_line(x - mark_size,
y - mark_size,
x + mark_size,
y + mark_size,
fill="blue",
width=mark_width)
canvas.create_line(x - mark_size,
y + mark_size,
x + mark_size,
y - mark_size,
fill="blue",
width=mark_width)
except:
pass
# function to be called when mouse is clicked
def printcoordsPos(event):
# outputting x and y coords to console
global colonies
colonies += 1
cx, cy = event2canvas(event, canvas)
color = "#32b33b"
canvas.create_line(cx - mark_size,
cy - mark_size,
cx + mark_size,
cy + mark_size,
fill=color,
width=mark_width)
canvas.create_line(cx - mark_size,
cy + mark_size,
cx + mark_size,
cy - mark_size,
fill=color,
width=mark_width)
coords.append((cx, cy, 1))
def printcoordsNeg(event):
cx, cy = event2canvas(event, canvas)
canvas.create_line(cx - mark_size,
cy - mark_size,
cx + mark_size,
cy + mark_size,
fill="#ed9121",
width=mark_width)
canvas.create_line(cx - mark_size,
cy + mark_size,
cx + mark_size,
cy - mark_size,
fill="#ed9121",
width=mark_width)
coords.append((cx, cy, 0))
def Undo(Event=None):
xy = coords.pop()
x = xy[0]
y = xy[1]
canvas.create_oval(x - 2,
y - 2,
x + 2,
y + 2,
outline="#9400D3",
fill="#9400D3")
global colonies
colonies -= 1
# mouseclick event
canvas.bind("<ButtonPress-1>", printcoordsPos)
canvas.bind("<ButtonPress-3>", Undo)
canvas.bind_all('<ButtonPress-2>', printcoordsNeg)
root.mainloop()
print(colonies)
return coords, coord_file
def drug_nums_to_mysql(path, year, choice, num):
"""
将历年药品每月用量及总和导入Mysql
@param path: 文件路径
@param year: 年份
@param choice: 药品类型
@param num: 展示数量
@return: null
"""
data = spark.read.format('parquet').load(path)
data = data.select('PersonalType', 'RegisterDate', 'DT', 'DrugName', 'Count', 'CompRatio_Type') \
.where("CompRatio_Type = '" + choice + "'") \
.where("DT = {}".format(year)) \
.drop('DT', 'CompRatio_Type')
# 处理RegisterDate,提取月份
data = data.withColumn('RegisterDate', data.RegisterDate.substr(6, 2)) \
.withColumnRenamed('RegisterDate', 'Month')
data = data.withColumn('Month', data.Month.cast(IntegerType())) \
.withColumn('Count', data.Count.cast(IntegerType())) \
.withColumn('DrugName', CD.changeNameUDF(data.DrugName)) \
.where('DrugName != "0"')
data_poor = data.where('PersonalType = 17').drop('PersonalType')
data_not_poor = data.where('PersonalType != 17').drop('PersonalType')
df_not_poor = get_data_temp(data_not_poor)
df_poor = get_data_temp(data_poor)
df_poor = df_poor.orderBy(df_poor['Sum'].desc())
all_drug_nums_poor = [['药名', '1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12']]
all_drug_nums_not_poor = [['药名', '1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12']]
conn = get_conn()
cur = conn.cursor()
t = 0
df_poor = df_poor.collect()
for i in df_poor:
print(str(t))
if t == int(num):
break
t += 1
temp_poor = []
temp_not_poor = []
try:
j = df_not_poor.select('*').where(df_not_poor.DrugName == str(i['DrugName'])).collect()[0]
print(i)
temp_poor.append(i['DrugName'])
temp_not_poor.append(i['DrugName'])
# 0 --> 建档立卡
# 1 --> 非建档立卡
cur.execute(
"INSERT INTO drugNumList VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
(i["DrugName"], i[1], i[2], i[3], i[4], i[5], i[6], i[7], i[8], i[9], i[10], i[11], i[12], year, 0,
choice, i['Sum']))
cur.execute(
"INSERT INTO drugNumList VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
(i["DrugName"], j[1], j[2], j[3], j[4], j[5], j[6], j[7], j[8], j[9], j[10], j[11], j[12], year, 1,
choice, j['Sum']))
except Exception as e:
print(e)
temp_poor.append(i['DrugName'])
temp_not_poor.append(i['DrugName'])
cur.execute(
"INSERT INTO drugNumList VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
(i["DrugName"], i[1], i[2], i[3], i[4], i[5], i[6], i[7], i[8], i[9], i[10], i[11], i[12], year, 0,
choice, i['Sum']))
cur.execute(
"INSERT INTO drugNumList VALUES(%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)",
(i["DrugName"], 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, year, 1, choice, 0))
conn.commit()
# all_nums = {
# 'poor': all_drug_nums_poor,
# 'not_poor': all_drug_nums_not_poor
# }
# cur.close()
# conn.close()
'''