Cross-referenceable figure numbers by section with python docx - python-2.7

I've been using python-docx to produce large documents full of tables and figures conforming with a standard template. I have discovered how to make them cross-referenceable using https://github.com/python-openxml/python-docx/issues/359 . However this labels my figures/tables starting at 1 within each section and continuing until the next section where it restarts from 1.
I would like the figure numbers to be dependent on the section number (i.e. 1st figure in 2nd section = Figure 2.1 etc.). Does anyone know if this is possible?
Currently the numbering is produced by the function:
def Table(paragraph):
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
run = run = paragraph.add_run()
r = run._r
fldChar = OxmlElement('w:fldChar')
fldChar.set(qn('w:fldCharType'), 'begin')
r.append(fldChar)
instrText = OxmlElement('w:instrText')
instrText.text = ' SEQ TableMain \* ARABIC \s 1 '
print instrText
r.append(instrText)
fldChar = OxmlElement('w:fldChar')
fldChar.set(qn('w:fldCharType'), 'end')
r.append(fldChar)
Called by the following code which also populates the table and table title and footer
table3 = document.add_table(rows=1, cols=1)
table3.cell(0,0).text="Table "
for paragraph in table4.cell(0,0).paragraphs:
paragraph.style = document.styles['Caption']
Table(paragraph)
paragraph.add_run(text="this is the full table name")
row_cells = table3.add_row().cells
call_func_that_makes_actual_table(row_cells[0],...)
row_cells = table3.add_row().cells
row_cells[0].text="Source: ..."
for paragraph in row_cells[0].paragraphs:
paragraph.style = document.styles['Source']
This produces a table like
this
Whereas I would like the table numbering like
this

Managed to work this out myself the solution is adding a further function:
def section(paragraph):
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
run = run = paragraph.add_run()
r = run._r
fldChar = OxmlElement('w:fldChar')
fldChar.set(qn('w:fldCharType'), 'begin')
r.append(fldChar)
instrText = OxmlElement('w:instrText')
instrText.text = ' STYLEREF 1 \s '
r.append(instrText)
fldChar = OxmlElement('w:fldChar')
fldChar.set(qn('w:fldCharType'), 'end')
r.append(fldChar)
and changing the call to:
for paragraph in table.cell(1,0).paragraphs:
paragraph.style = document.styles['Caption']
section(paragraph)
paragraph.add_run(text=".")
Figure(paragraph)
paragraph.add_run(text=": this is the full table name")

Related

Select row with regex instead of unique value

Hello everyone I'm making a really simple lookup in a pandas dataframe, what I need to do is to lookup for the input I'm typing as a regex instead of == myvar
So far this is what I got which is very inneficient because there's a lot of Names in my DataFrame that instead of matching a list of them which could be
Name LastName
NAME 1 Some Awesome
Name 2 Last Names
Nam e 3 I can keep going
Bane Writing this is awesome
BANE 114 Lets continue
However this is what I got
import pandas as pd
contacts = pd.read_csv("contacts.csv")
print("regex contacts")
nameLookUp = input("Type the name you are looking for: ")
print(nameLookUp)
desiredRegexVar = contacts.loc[contacts['Name'] == nameLookUp]
print(desiredRegexVar)
I have to type 'NAME 1' or 'Nam e 3' in order results or I wont get any at all, I tried using this but it didnt work
#regexVar = "^" + contacts.filter(regex = nameLookUp)
Thanks for the answer #Code Different
The code looks like this
import pandas as pd
import re
namelookup = input("Type the name you are looking for: ")
pattern = '^' + re.escape(namelookup)
match = contactos['Cliente'].str.contains(pattern, flags=re.IGNORECASE, na=False)
print(contactos[match])
Use Series.str.contains. Tweak the pattern as appropriate:
import re
pattern = '^' + re.escape(namelookup)
match = contacts['Name'].str.contains(pattern, flags=re.IGNORECASE)
contacts[match]

using pd.read_sql() to extract large data (>5 million records) from oracle database, making the sql execution very slow

Initially tried using pd.read_sql().
Then I tried using sqlalchemy, query objects but none of these methods are
useful as the sql getting executed for long time and it never ends.
I tried using Hints.
I guess the problem is the following: Pandas creates a cursor object in the
background. With cx_Oracle we cannot influence the "arraysize" parameter which
will be used thereby, i.e. always the default value of 100 will be used which
is far too small.
CODE:
import pandas as pd
import Configuration.Settings as CS
import DataAccess.Databases as SDB
import sqlalchemy
import cx_Oracle
dfs = []
DBM = SDB.Database(CS.DB_PRM,PrintDebugMessages=False,ClientInfo="Loader")
sql = '''
WITH
l AS
(
SELECT DISTINCT /*+ materialize */
hcz.hcz_lwzv_id AS lwzv_id
FROM
pm_mbt_materialbasictypes mbt
INNER JOIN pm_mpt_materialproducttypes mpt ON mpt.mpt_mbt_id = mbt.mbt_id
INNER JOIN pm_msl_materialsublots msl ON msl.msl_mpt_id = mpt.mpt_id
INNER JOIN pm_historycompattributes hca ON hca.hca_msl_id = msl.msl_id AND hca.hca_ignoreflag = 0
INNER JOIN pm_tpm_testdefprogrammodes tpm ON tpm.tpm_id = hca.hca_tpm_id
inner join pm_tin_testdefinsertions tin on tin.tin_id = tpm.tpm_tin_id
INNER JOIN pm_hcz_history_comp_zones hcz ON hcz.hcz_hcp_id = hca.hca_hcp_id
WHERE
mbt.mbt_name = :input1 and tin.tin_name = 'x1' and
hca.hca_testendday < '2018-5-31' and hca.hca_testendday > '2018-05-30'
),
TPL as
(
select /*+ materialize */
*
from
(
select
ut.ut_id,
ut.ut_basic_type,
ut.ut_insertion,
ut.ut_testprogram_name,
ut.ut_revision
from
pm_updated_testprogram ut
where
ut.ut_basic_type = :input1 and ut.ut_insertion = :input2
order by
ut.ut_revision desc
) where rownum = 1
)
SELECT /*+ FIRST_ROWS */
rcl.rcl_lotidentifier AS LOT,
lwzv.lwzv_wafer_id AS WAFER,
pzd.pzd_zone_name AS ZONE,
tte.tte_tpm_id||'~'||tte.tte_testnumber||'~'||tte.tte_testname AS Test_Identifier,
case when ppd.ppd_measurement_result > 1e15 then NULL else SFROUND(ppd.ppd_measurement_result,6) END AS Test_Results
FROM
TPL
left JOIN pm_pcm_details pcm on pcm.pcm_ut_id = TPL.ut_id
left JOIN pm_tin_testdefinsertions tin ON tin.tin_name = TPL.ut_insertion
left JOIN pm_tpr_testdefprograms tpr ON tpr.tpr_name = TPL.ut_testprogram_name and tpr.tpr_revision = TPL.ut_revision
left JOIN pm_tpm_testdefprogrammodes tpm ON tpm.tpm_tpr_id = tpr.tpr_id and tpm.tpm_tin_id = tin.tin_id
left JOIN pm_tte_testdeftests tte on tte.tte_tpm_id = tpm.tpm_id and tte.tte_testnumber = pcm.pcm_testnumber
cross join l
left JOIN pm_lwzv_info lwzv ON lwzv.lwzv_id = l.lwzv_id
left JOIN pm_rcl_resultschipidlots rcl ON rcl.rcl_id = lwzv.lwzv_rcl_id
left JOIN pm_pcm_zone_def pzd ON pzd.pzd_basic_type = TPL.ut_basic_type and pzd.pzd_pcm_x = lwzv.lwzv_pcm_x and pzd.pzd_pcm_y = lwzv.lwzv_pcm_y
left JOIN pm_pcm_par_data ppd ON ppd.ppd_lwzv_id = l.lwzv_id and ppd.ppd_tte_id = tte.tte_id
'''
#method1: using query objects.
Q = DBM.getQueryObject(sql)
Q.execute({"input1":'xxxx',"input2":'yyyy'})
while not Q.AtEndOfResultset:
print Q
#method2: using sqlalchemy
connectstring = "oracle+cx_oracle://username:Password#(description=
(address_list=(address=(protocol=tcp)(host=tnsconnect string)
(port=pertnumber)))(connect_data=(sid=xxxx)))"
engine = sqlalchemy.create_engine(connectstring, arraysize=10000)
df_p = pd.read_sql(sql, params=
{"input1":'xxxx',"input2":'yyyy'}, con=engine)
#method3: using pd.read_sql()
df_p = pd.read_sql_query(SQL_PCM, params=
{"input1":'xxxx',"input2":'yyyy'},
coerce_float=True, con= DBM.Connection)
It would be great if some one could help me out in this. Thanks in advance.
And yet another possibility to adjust the array size without needing to create oraaccess.xml as suggested by Chris. This may not work with the rest of your code as is, but it should give you an idea of how to proceed if you wish to try this approach!
class Connection(cx_Oracle.Connection):
def __init__(self):
super(Connection, self).__init__("user/pw#dsn")
def cursor(self):
c = super(Connection, self).cursor()
c.arraysize = 5000
return c
engine = sqlalchemy.create_engine(creator=Connection)
pandas.read_sql(sql, engine)
Here's another alternative to experiment with.
Set a prefetch size by using the external configuration available to Oracle Call Interface programs like cx_Oracle. This overrides internal settings used by OCI programs. Create an oraaccess.xml file:
<?xml version="1.0"?>
<oraaccess xmlns="http://xmlns.oracle.com/oci/oraaccess"
xmlns:oci="http://xmlns.oracle.com/oci/oraaccess"
schemaLocation="http://xmlns.oracle.com/oci/oraaccess
http://xmlns.oracle.com/oci/oraaccess.xsd">
<default_parameters>
<prefetch>
<rows>1000</rows>
</prefetch>
</default_parameters>
</oraaccess>
If you use tnsnames.ora or sqlnet.ora for cx_Oracle, then put the oraaccess.xml file in the same directory. Otherwise, create a new directory and set the environment variable TNS_ADMIN to that directory name.
cx_Oracle needs to be using Oracle Client 12c, or later, libraries.
Experiment with different sizes.
See OCI Client-Side Deployment Parameters Using oraaccess.xml.

CAD to Feature Class

import arcpy
fc = r'H:\H-ONUS UTILITY DATA GIS\As_Builts\2014\RandolphPoint_Phase2\789-AS-BUILT 8-7-13.dwg\Polyline'
out_gdb = r'H:\H-ONUS UTILITY DATA GIS\As_Builts\2014\RandolphPoint_Phase2\RandolphPoint.gdb.gdb'
field = 'Layer'
values = [row[0] for row in arcpy.da.SearchCursor(fc, (field))]
uniqueValues = set(Values)
for value in uniqueValues:
sql = """Layer" = '{0}'""".format(Value)
name = arcpy.ValidateTableName(value,out_gdb)
arcpy.FeatureClassToFeatureClass_conversion(fc, out_gdb, name, sql)
I am trying to convert CAD(dwg) to ArcGIS 10.2.2 Feature Classes using a file geodatase as the workspace. I was just taught this code at an ESRI conference and of course it worked beautifully for the insturtor.
My error I am getting is "NameError:name'Values' is not defined" however I did define it as values = [row[0] for row in arcpy.da.SearchCursor(fc, (field))] I have been working hours on this, it would help out my job considerably.
Python variables are case-sensitive.
You've declared values with a lower-case v, but you're referring to it on the next line with an upper-case V.
(Same with value/Value further down.
import arcpy
fc = r'H:\H-ONUS UTILITY DATA GIS\As_Builts\2014\RandolphPoint_Phase2\789ASBUILT.dwg\Polyline'
out_gdb = r'H:\H-ONUS UTILITY DATA GIS\As_Builts\2014\RandolphPoint_Phase2\RandolphPoint.gdb'
field = 'Layer'
value = [row[0] for row in arcpy.da.SearchCursor(fc, (field))]
uniquevalues = set(value)
for value in uniquevalues:
sql = """"Layer" = '{0}'""".format(value)
name = arcpy.ValidateTableName(value,out_gdb)
arcpy.FeatureClassToFeatureClass_conversion(fc, out_gdb, name, sql)
Here is the solution, I had an extra .gdb in the geodatabase path
my word value was values so had to take the s off
and also in my sql statement I was missing a " before the word Layer
If anyone is reading this just change the individual parameters and it works beautifully!
thanks Juffy for responding and trying to help me out
Cartogal

Parsing HTML Tables with BS4

I've been trying different methods of scraping data from this site (http://nflcombineresults.com/nflcombinedata.php?year=1999&pos=WR&college=) and can't seem to get any of them to work. I've tried playing with the indices given, but can't seem to make it work. I think I've tried too many things at this point,so if someone could point me in the right direction I would really appreciate it.
I would like to pull all of the information and export it to a .csv file, but at this point I'm just trying to get the name and position to print to get started.
Here's my code:
import urllib2
from bs4 import BeautifulSoup
import re
url = ('http://nflcombineresults.com/nflcombinedata.php?year=1999&pos=&college=')
page = urllib2.urlopen(url).read()
soup = BeautifulSoup(page)
table = soup.find('table')
for row in table.findAll('tr')[0:]:
col = row.findAll('tr')
name = col[1].string
position = col[3].string
player = (name, position)
print "|".join(player)
Here's the error I'm getting:
line 14, in name = col[1].string
IndexError: list index out of range.
--UPDATE--
Ok, I've made a little progress. It now allows me to go from start to finish, but it requires knowing how many rows are in the table. How would I get it to just go through them until the end?
Updated Code:
import urllib2
from bs4 import BeautifulSoup
import re
url = ('http://nflcombineresults.com/nflcombinedata.php?year=1999&pos=&college=')
page = urllib2.urlopen(url).read()
soup = BeautifulSoup(page)
table = soup.find('table')
for row in table.findAll('tr')[1:250]:
col = row.findAll('td')
name = col[1].getText()
position = col[3].getText()
player = (name, position)
print "|".join(player)
I figured it out after only 8 hours or so. Learning is fun. Thanks for the help Kevin!
It now includes the code to output the scraped data to a csv file. Next up is taking that data and filtering out for certain positions....
Here's my code:
import urllib2
from bs4 import BeautifulSoup
import csv
url = ('http://nflcombineresults.com/nflcombinedata.php?year=2000&pos=&college=')
page = urllib2.urlopen(url).read()
soup = BeautifulSoup(page)
table = soup.find('table')
f = csv.writer(open("2000scrape.csv", "w"))
f.writerow(["Name", "Position", "Height", "Weight", "40-yd", "Bench", "Vertical", "Broad", "Shuttle", "3-Cone"])
# variable to check length of rows
x = (len(table.findAll('tr')) - 1)
# set to run through x
for row in table.findAll('tr')[1:x]:
col = row.findAll('td')
name = col[1].getText()
position = col[3].getText()
height = col[4].getText()
weight = col[5].getText()
forty = col[7].getText()
bench = col[8].getText()
vertical = col[9].getText()
broad = col[10].getText()
shuttle = col[11].getText()
threecone = col[12].getText()
player = (name, position, height, weight, forty, bench, vertical, broad, shuttle, threecone, )
f.writerow(player)
I can't run your script due to firewall permissions, but I believe the problem is on this line:
col = row.findAll('tr')
row is a tr tag, and you're asking BeautifulSoup to find all tr tags within that tr tag. You probably meant to do:
col = row.findAll('td')
Furthermore, since the actual text isn't directly inside the tds but is also hidden within nested divs and as, it may be useful to use the getText method instead of .string:
name = col[1].getText()
position = col[3].getText()
Simple way to parse the table column wise:
def table_to_list(table):
data = []
all_th = table.find_all('th')
all_heads = [th.get_text() for th in all_th]
for tr in table.find_all('tr'):
all_th = tr.find_all('th')
if all_th:
continue
all_td = tr.find_all('td')
data.append([td.get_text() for td in all_td])
return list(zip(all_heads, *data))
r = requests.get(url, headers=headers)
bs = BeautifulSoup(r.text)
all_tables = bs.find_all('table')
table_to_list(all_tables[0])

Attribute Error for strings created from lists

I'm trying to create a data-scraping file for a class, and the data I have to scrape requires that I use while loops to get the right data into separate arrays-- i.e. for states, and SAT averages, etc.
However, once I set up the while loops, my regex that cleared the majority of the html tags from the data broke, and I am getting an error that reads:
Attribute Error: 'NoneType' object has no attribute 'groups'
My Code is:
import re, util
from BeautifulSoup import BeautifulStoneSoup
# create a comma-delineated file
delim = ", "
#base url for sat data
base = "http://www.usatoday.com/news/education/2007-08-28-sat-table_N.htm"
#get webpage object for site
soup = util.mysoupopen(base)
#get column headings
colCols = soup.findAll("td", {"class":"vaTextBold"})
#get data
dataCols = soup.findAll("td", {"class":"vaText"})
#append data to cols
for i in range(len(dataCols)):
colCols.append(dataCols[i])
#open a csv file to write the data to
fob=open("sat.csv", 'a')
#initiate the 5 arrays
states = []
participate = []
math = []
read = []
write = []
#split into 5 lists for each row
for i in range(len(colCols)):
if i%5 == 0:
states.append(colCols[i])
i=1
while i<=250:
participate.append(colCols[i])
i = i+5
i=2
while i<=250:
math.append(colCols[i])
i = i+5
i=3
while i<=250:
read.append(colCols[i])
i = i+5
i=4
while i<=250:
write.append(colCols[i])
i = i+5
#write data to the file
for i in range(len(states)):
states = str(states[i])
participate = str(participate[i])
math = str(math[i])
read = str(read[i])
write = str(write[i])
#regex to remove html from data scraped
#remove <td> tags
line = re.search(">(.*)<", states).groups()[0] + delim + re.search(">(.*)<", participate).groups()[0]+ delim + re.search(">(.*)<", math).groups()[0] + delim + re.search(">(.*)<", read).groups()[0] + delim + re.search(">(.*)<", write).groups()[0]
#append data point to the file
fob.write(line)
Any ideas regarding why this error suddenly appeared? The regex was working fine until I tried to split the data into different lists. I have already tried printing the various strings inside the final "for" loop to see if any of them were "None" for the first i value (0), but they were all the string that they were supposed to be.
Any help would be greatly appreciated!
It looks like the regex search is failing on (one of) the strings, so it returns None instead of a MatchObject.
Try the following instead of the very long #remove <td> tags line:
out_list = []
for item in (states, participate, math, read, write):
try:
out_list.append(re.search(">(.*)<", item).groups()[0])
except AttributeError:
print "Regex match failed on", item
sys.exit()
line = delim.join(out_list)
That way, you can find out where your regex is failing.
Also, I suggest you use .group(1) instead of .groups()[0]. The former is more explicit.