I have the date of 1515 in my data set column 4, is there any way to bypass this error?
cols[4] = cols[4] and cols[4].strftime("%d/%m/%Y") or ""
ValueError: year=1515 is before 1900; the datetime strftime() methods require year >= 1900
Here is the exact code:
cursor.execute(SQL)
filename = r"C:\Projects\OPEN_KCI3.csv"
with open(filename, "wb") as fout:
writer = csv.writer(fout)
#writer.writerow([i[0] for i in cursor.description ]) # heading row
for row in cursor.fetchall():
cols = list(row)
cols[3] = cols[3] and cols[3].strftime("%d/%m/%Y") or ""
cols[4] = cols[4] and cols[4].strftime("%d/%m/%Y") or ""
writer.writerow(cols)
cursor.close()
connection.close()
Related
The error occurs in the last step of this code when I try to sort a list using SORTED. I get the error message that a "list object is not callable". I want to use the SORTED and not the SORT function for this.
from csv import reader
import datetime as dt
open_file = open("hacker_news.csv")
read_file = reader(open_file)
hn = list(read_file)
headers = hn[0]
hn = hn[1:]
def explore_data(dataset,start,finish,col_rows=True):
dataset_slice = dataset[start:finish]
for row in dataset_slice:
print(row)
print('\n')
if col_rows:
print('rows:' , len(dataset))
print('columns:' , len(dataset[0]))
ask_posts = []
show_posts = []
other_posts = []
for row in hn:
title = row[1]
if title.lower().startswith("ask hn"):
ask_posts.append(row)
elif title.lower().startswith("show hn"):
show_posts.append(row)
else:
other_posts.append(row)
total_ask_comments = 0
total_show_comments = 0
total = 0
for row in ask_posts:
total += 1
num_comments = int(row[4])
total_ask_comments += num_comments
avg_ask_comments = total_ask_comments/total
print(avg_ask_comments)
for row in show_posts:
total += 1
num_comments = int(row[4])
total_show_comments += num_comments
avg_show_comments = total_show_comments/total
print(avg_show_comments)
result_list = []
for row in ask_posts:
created_at = row[6]
num_comments = int(row[4])
result_list.append([created_at,num_comments])
counts_by_hour = {}
comments_by_hour = {}
for row in result_list:
comment = row[1]
date_time = row[0]
date_time = dt.datetime.strptime(date_time,'%m/%d/%Y %H:%M')
hour = date_time.strftime('%H')
if hour not in counts_by_hour:
counts_by_hour[hour] = 1
comments_by_hour[hour] = comment
else:
counts_by_hour[hour] += 1
comments_by_hour[hour] += comment
for hour in counts_by_hour:
if hour in comments_by_hour:
avg = round(comments_by_hour[hour]/counts_by_hour[hour],2)
avg_by_hour.append([hour,avg])
for row in avg_by_hour:
swap_avg_by_hour.append([row[1], row[0]])
print(swap_avg_by_hour)
sorted_swap = sorted(swap_avg_by_hour, reverse=True)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-49-307863a4b1cd> in <module>
6 print(swap_avg_by_hour)
7
----> 8 sorted_swap = sorted(swap_avg_by_hour, reverse=True)
9
10 print(sorted_swap)
TypeError: 'list' object is not callable
Not sure how to upload the csv as don't see an upload option. Is there an obvious error in the code? or can someone help with instructions to upload the csv file?
You need to declare these 2 lists before appnding avg_by_hour = [] swap_avg_by_hour= []
I have copied the text file to excel sheet separating cells by ; delimiter.
I need to plot a chart using the same file which I achieved. Since all the values copied are type=str my chart gives me wrong points.
Please suggest to overcome this. Plot is should be made of int values
from datetime import date
from openpyxl import Workbook,load_workbook
from openpyxl.chart import (
LineChart,
Reference,
Series,
)
from openpyxl.chart.axis import DateAxis
excelfile = "C:\Users\lenovo\Desktop\how\openpychart.xlsx"
wb = Workbook()
ws = wb.active
f = open("C:\Users\lenovo\Desktop\sample.txt")
data = []
num = f.readlines()
for line in num:
line = line.split(";")
ws.append(line)
f.close()
wb.save(excelfile)
wb.close()
wb = load_workbook(excelfile, data_only=True)
ws = wb.active
c1 = LineChart()
c1.title = "Line Chart"
##c1.style = 13
c1.y_axis.title = 'Size'
c1.x_axis.title = 'Test Number'
data = Reference(ws, min_col=6, min_row=2, max_col=6, max_row=31)
series = Series(data, title='4th average')
c1.append(series)
data = Reference(ws, min_col=7, min_row=2, max_col=7, max_row=31)
series = Series(data, title='Defined Capacity')
c1.append(series)
##c1.add_data(data, titles_from_data=True)
# Style the lines
s1 = c1.series[0]
s1.marker.symbol = "triangle"
s1.marker.graphicalProperties.solidFill = "FF0000" # Marker filling
s1.marker.graphicalProperties.line.solidFill = "FF0000" # Marker outline
s1.graphicalProperties.line.noFill = True
s2 = c1.series[1]
s2.graphicalProperties.line.solidFill = "00AAAA"
s2.graphicalProperties.line.dashStyle = "sysDot"
s2.graphicalProperties.line.width = 100050 # width in EMUs
##s2 = c1.series[2]
##s2.smooth = True # Make the line smooth
ws.add_chart(c1, "A10")
##
##from copy import deepcopy
##stacked = deepcopy(c1)
##stacked.grouping = "stacked"
##stacked.title = "Stacked Line Chart"
##ws.add_chart(stacked, "A27")
##
##percent_stacked = deepcopy(c1)
##percent_stacked.grouping = "percentStacked"
##percent_stacked.title = "Percent Stacked Line Chart"
##ws.add_chart(percent_stacked, "A44")
##
### Chart with date axis
##c2 = LineChart()
##c2.title = "Date Axis"
##c2.style = 12
##c2.y_axis.title = "Size"
##c2.y_axis.crossAx = 500
##c2.x_axis = DateAxis(crossAx=100)
##c2.x_axis.number_format = 'd-mmm'
##c2.x_axis.majorTimeUnit = "days"
##c2.x_axis.title = "Date"
##
##c2.add_data(data, titles_from_data=True)
##dates = Reference(ws, min_col=1, min_row=2, max_row=7)
##c2.set_categories(dates)
##
##ws.add_chart(c2, "A61")
### setup and append the first series
##values = Reference(ws, (1, 1), (9, 1))
##series = Series(values, title="First series of values")
##chart.append(series)
##
### setup and append the second series
##values = Reference(ws, (1, 2), (9, 2))
##series = Series(values, title="Second series of values")
##chart.append(series)
##
##ws.add_chart(chart)
wb.save(excelfile)
wb.close()
I have modified below code in for loop and it worked.
f = open("C:\Users\lenovo\Desktop\sample.txt")
data = []
num = f.readlines()
for line in num:
line = line.split(";")
new_line=[]
for x in line:
if x.isdigit():
x=int(x)
new_line.append(x)
else:
new_line.append(x)
ws.append(new_line)
f.close()
wb.save(excelfile)
wb.close()
For each list,for each value check if its a digit, if yes converts to integer and store in another list.
Using x=map(int,x) didnt work since I have character values too.
I felt above is much more easy than using x=map(int,x) with try and Except
Thanks
Basha
I am trying to create an application where it pulls the information from website using python and I am using datetime formats.
def constructYFURL(ticker,start_date,end_date,freq):
start_date = datetime.strptime(start_date,"%Y-%m-%d").date()
end_date = datetime.strptime(end_date,"%Y-%m-%d").date()
s=ticker.replace("^","%5E")
if start_date.month-1<10:
a="0"+str(start_date.month-1)
else:
a=str(start_date.month-1)
# Also the month always has 2 digits
b=str(start_date.day)
c=str(start_date.year)
if end_date.month - 1 < 10:
d = "0" + str(end_date.month - 1)
else:
d = str(end_date.month - 1)
e=str(end_date.day)
f=str(end_date.year)
`enter code here`g=freq
yfURL = "http://real-chart.finance.yahoo.com/table.csv? s="+s+"&a="+a+"&b="+b+"&c="+c+"&d="+d+"&e="+e+"&f="+f+"&g="+g+"&ignore=.csv"
return yfURL
from download import constructYFURL
ticker = "AAPL"
start_date = "2016-01-01"
end_date = " 2017-03-06"
freq = "d"
yfURL = constructYFURL(ticker,start_date,end_date,freq)
print yfURL
I am getting a following error saying:
ValueError: time data ' 2017-03-06' does not match format '%Y-%m-%d'
You have an extra leading space in:
end_date = " 2017-03-06"
remove it and the error you're getting goes away and the program runs
Better formatted code:
def constructYFURL(ticker,start_date,end_date,freq):
start_date = datetime.strptime(start_date,"%Y-%m-%d").date()
end_date = datetime.strptime(end_date,"%Y-%m-%d").date()
s=ticker.replace("^","%5E")
if start_date.month-1<10:
a="0"+str(start_date.month-1)
else:
a=str(start_date.month-1)
# Also the month always has 2 digits
b=str(start_date.day)
c=str(start_date.year)
if end_date.month - 1 < 10:
d = "0" + str(end_date.month - 1)
else:
d = str(end_date.month - 1)
e=str(end_date.day)
f=str(end_date.year)
g=freq
yfURL = "http://real-chart.finance.yahoo.com/table.csv? s="+s+"&a="+a+"&b="+b+"&c="+c+"&d="+d+"&e="+e+"&f="+f+"&g="+g+"&ignore=.csv"
return yfURL
ticker = "AAPL"
start_date = "2016-01-01"
end_date = "2017-03-06"
freq = "d"
yfURL = constructYFURL(ticker,start_date,end_date,freq)
print yfURL
I'm trying to write a script that formats the date in a log file. The log file is meant to be read by excel after the conversion.
import datetime
def excel_date(date1):
temp = dt.datetime(1899, 12, 30)
delta = date1 - temp
return float(delta.days) + (float(delta.seconds) / 86400)
data=open(".\input.log").read()
file_ = open('output.log', 'w')
for row in data.split('\n'):
prefix = row[:1]
sdate = row[1:29]
suffix = row[30:]
offset = datetime.timedelta(0)
dt = datetime.datetime.strptime(sdate, '%a %b %d %H:%M:%S.%f %Y') + offset
excelDate = excel_date(dt)
file_.write(dt.strftime('%d.%m.%Y %H:%M:%S') + "\t" + excelDate + "\t"+ suffix + "\n")
file_.close()
The problem occurs when I try to use the excel_date function. I know that strptime returns a string and that the function expects a datetime object. Is there a way of creating a datetime object from strptime or converting the string into one?
Thanks
Here is the piece I am trying to write the value inside existing excel sheet in particular cell but value is not printing inside that sheet,how to write that value,here I used xlutils.copy
from datetime import datetime, timedelta, date
from xlrd import open_workbook
from xlwt import Workbook
from xlutils.copy import copy
import xlrd
import datetime
book = open_workbook('Data.xlsx')
sheet = book.sheet_by_index(0)
# read header values into the list
keys = [sheet.cell(0, col_index).value for col_index in xrange(sheet.ncols)]
dict_list = []
#read the excel sheet data into list
for row_index in xrange(1, sheet.nrows):
d = {keys[col_index]: sheet.cell(row_index, col_index).value
for col_index in xrange(sheet.ncols)}
dict_list.append(d)
TotalEffort = 0
#convert the integer date to YMD format
for count in range(len(dict_list)):
year, month, day, hour, minute, second = xlrd.xldate_as_tuple(dict_list[count]["Date"],book.datemode)
#print week number
if datetime.date.today().isocalendar()[1] == date(year, month, day).isocalendar()[1]:
TotalEffort = TotalEffort+dict_list[count]["Effort"]
weeknum = str(datetime.date.today().isocalendar()[1])
Total = str(TotalEffort)
print " Effort for week"+weeknum+" is: "+Total+"hours"
rb = open_workbook('output.xlsx')
ws = rb.sheet_by_index(0)
for rowidx in range(ws.nrows):# number of rows in sheets
row = ws.row(rowidx)# count row from 0 and get it frm sheet
for colidx, cell in enumerate(row):#read all rows in sheets
if cell.value == "search word":
print 'row ' ,rowidx
print 'column' ,colidx
cur_row = rowidx+2
cur_col = colidx+36
wb = copy(rb)
#pic first sheet
shw = wb.get_sheet(0)
value = str(Total)
#writing to shw
shw.write(cur_row,cur_col,'value')