def read_from_dir(cls, path, outexcel=False, outpath=None):
files = os.listdir(path)
if outexcel:
moutexcel = Excel(outpath)
moutexcel.new().append([[item, item] for item in files], "sheet1")
moutexcel.close()
else:
return files
def __init__(self, file_name=None):
mexcel = Excel(file_name)
self._raw_acode_data = mexcel.read()
self.region_list = [re.sub('\s+','',item[1]) for item in self._raw_acode_data[1:]]
self.admin_code_dict = OrderedDict([(re.sub('\s+','',item[1]),str(int(item[0]))) for item in self._raw_acode_data[1:]])
self.code_admin_dict = OrderedDict([(str(int(item[0])),re.sub('\s+','',item[1])) for item in self._raw_acode_data[1:]])
self._create_relationship()
# coding=UTF-8
import pandas as pd
import numpy as np
from libs.database.class_cgssdatabase import CgssDatabase
from libs.file.class_Excel import Excel
filename = r"D:\data\student.xls"
Path = r"D:\data\labdata"
mexcel = Excel(filename)
mdata = mexcel.read()
mdata = [item[1] for item in mdata]
cgdb = CgssDatabase(year=2013)
pdata = cgdb.variables(
variables=[
["a2", False],
["a3a", False],
["a4", False],
["a7a", False],
["a8a", False],
["a8b", False],
["a10", False],
["a18", False],
["a59j", False],
["a69", False],
["a89b", False],
]
)
pdata.columns = [
"A10政治面貌",
# coding=UTF-8
import numpy as np
import pandas as pd
from libs.file.class_Excel import Excel
# 0. 导入学生名单
STUDENT_FILE = 'E:\\temp\\lab\\student.xls'
mexcel = Excel(STUDENT_FILE)
student_list = mexcel.read()
students = [item[1] for item in student_list]
# 1. 生成学生数据和答案
out_path = 'E:\\temp\\lab\\'
file_name = '_data.xls'
rules1 = [1,2,4]
rules3 = [3,7,9]
result = [['student','model1','','','','model2','','','','model3','','','','model4','','','']]
for student in students:
mu, sigma = 0, np.random.randint(1,20)/10
miu = np.random.normal(mu, sigma, 1000)
x1 = np.random.randint(1,100,1000)
x2 = 5 + np.random.randint(1,5)*x1/10 + np.random.normal(mu, 0.1, 1000)
x3 = np.random.randint(1,200,1000)
pdata = pd.DataFrame({'x1':x1,'x2':x2,'x3':x3})
one_student_coefs = [student]
for i in range(0,4):
constant = np.random.randint(1,100,1)
coefs = np.random.randint(0,10,3)
if re.match('^(-)?\d+((\.|．)\d+)?$',new_item) is not None:
new_item = re.sub('．','.',new_item)
new_row.append(float(new_item))
else:
all = False
new_row.append(item)
return new_row,all
if __name__ == '__main__':
filename = r'E:\data\procedure\Process\reduction\data\admincode\2003.xls'
acodefile = AdminCodeFile(filename)
filename = r'E:\data\procedure\Process\reduction\data\2003_prefecture\3_3_按三次业人员就业状况_地级市_2003.xls'
mexcel = WinExcel(filename)
mdata = mexcel.read()
reduction = CitydataReduction(mdata,acodefile)
reduction.reduction()
ndata = reduction.second_data
print(reduction.second_data)
outfile = r'd:\data\demo.xlsx'
moutexcel = Excel(outfile)
moutexcel.new().append(ndata, 'mysheet')
moutexcel.close()
source_file = os.path.join(current_import_dir, file)
# 目标文件
file_name = re.split("\.", file)[0]
new_file_name = "".join([file_name, "_first_step.xlsx"])
new_delete_name = "".join([file_name, "_deleted.xlsx"])
target_file = os.path.join(current_export_path, new_file_name)
delete_file = os.path.join(current_export_path, new_delete_name)
# 如果目标文件存在，那么跳过
if os.path.exists(target_file):
print("Here it is! ", file)
continue
# 从excel文件读入数据，构建CitydataReduction对象
# mexcel = WinExcel(source_file)
mexcel = Excel(source_file)
sdata = mexcel.read()
if abnormal:
ndata = []
first_part = []
second_part = []
for row in sdata:
if set(row) == {None}:
if len(first_part) < 1:
continue
else:
ndata.extend(first_part)
ndata.extend(second_part)
first_part = []
second_part = []
first_part.append(row[0:region_col])
result = []
journals = json.load(open(r'E:\gitrobot\files\publication\ssci_geography_json.txt'))
for journal in journals:
if journal[1] not in impact_factor_journals:
result.append([journal[0].upper(),journal[1],None])
else:
result.append([journal[0].upper(),journal[1],impact_factor_journals[journal[1]]])
# 2. output
for record in result:
print(record)
outfile = r'd:\down\tmp_journal.xlsx'
moutexcel = Excel(outfile)
moutexcel.new().append(result, 'sheet1')
moutexcel.close()'''
mongo = MongoDB()
mongo.connect('publication','WesternJournal')
filename = r'd:\down\journals.xlsx'
mexcel = Excel(filename)
mdata = mexcel.read(sheet=4)
result = []
for item in mdata[1:]:
if item[2] == '':
result.append({'journal':item[0],'SSIN':item[1],'IF':None})
else:
result.append({'journal':item[0],'SSIN':item[1],'IF':item[2]})
#for j in result:
# mongo.collection.insert_one(j)
