trying to get the lastest entry on a data frame - python

I'm using this code to make the top 10 most common names on my dataframe
df_faces_nombre = df_faces.groupby(["Nombre"])
top_names = df_faces_nombre.count().sort_values(by=['foto'], ascending=False).iloc[0:10]["foto"].index
for name in top_names:
fotos = df_faces_nombre.get_group(name)["foto"]
os.mkdir(TOP_DATA + name)
for foto in fotos:
if type(foto) == str and os.path.exists(DATA_DIR+foto):
try:
copyfile(DATA_DIR+foto, TOP_DATA + name + '/' + foto)
except:
print(foto)
Now I'm trying to make a new one to sort the 10 less common names, I thought using something similar in this way
low_names = df_faces_nombre.count().sort_values(by=['foto'], ascending=True).iloc[0:100]["foto"].index
for name in low_names:
fotos = df_faces_nombre.get_group(name)["foto"]
os.mkdir(LOWER_DATA + name)
for foto in fotos:
if type(foto) == str and os.path.exists(DATA_DIR+foto):
try:
copyfile(DATA_DIR+foto, LOWER_DATA + name + '/' + foto)
except:
print(foto)
The problem here is that the second code only copy the folders and not the pictures (sad face) i was hoping that you can help me to solve this, thanks in advance

solved there were a lot of names w/o pictures the code works well

Related

Passing the objects created in a class to the global workspace

I'm trying to figure out how to make the objects I create inside a definition appear on the same workspace as my "name == main" area, so I can call it in other definitions. I don't think I can use a simple "return" statement in my def, because my function is designed to create n-number of objects of a particular class.
def book_to_object(subfolders):
# converts my dictionary of book titles and volumes into individual book objects
for key, val in subfolders.items():
title = replace_spaces_with_underscores(key)
# check to see if book already exists in the registry
if title in [book.name for book in Book._registry]:
print("Book already exists")
else:
exec(title + " = Book(subfolders ,key, Fpath)")
The whole program below.
I'm calling this def from my if __name__ == '__main__': function
print("Done")
#converts my dictionary of book titles and volumes into individual book objects
book_to_object(subfolders)
Originally I had the code in my def in the name=main area of my code but I wanted to reduce the clutter and make it into a definition to give me more flexibility later.
The whole program below.
import os
#get date modified time of a file to determine which file is the newest
def get_date_modified(file):
return os.path.getmtime(file)
#replace spaces with underscores in a string
def replace_spaces_with_underscores(string):
aa = string.replace(" ", "_")
bb= aa.replace('-', '_')
cc= bb.replace("__", "_")
title = cc.replace("__", "_")
return title
# create a list of volumes that have not been exported
def get_unexported_volumes(self):
unexported_volumes = []
for volume in self.volumes:
if volume not in self.last_exported:
unexported_volumes.append(volume)
return unexported_volumes
def book_to_object(subfolders):
# converts my dictionary of book titles and volumes into individual book objects
for key, val in subfolders.items():
title = replace_spaces_with_underscores(key)
# check to see if book already exists in the registry
if title in [book.name for book in Book._registry]:
print("Book already exists")
else:
exec(title + " = Book(subfolders ,key, Fpath)")
class Book(object):
#__metaclass__ = IterBook
_registry = []
#constructor
def __init__(self, my_dict, key, Fpath):
self._registry.append(self)
self.name = key
self.volumes = my_dict[key]
self.Filepath = Fpath + "/" +self.name
#self.last_exported = self.volumes[0]
self.last_exported = ""
self.newest = self.volumes[-1]
self.last_downloaded = self.volumes[-1]
self.last_converted = self.volumes[-1]
self.last_exported_date = get_date_modified(self.Filepath + "/" + self.last_exported)
self.newest_date = get_date_modified(self.Filepath + "/" + self.newest)
self.last_downloaded_date = get_date_modified(self.Filepath + "/" + self.last_downloaded)
self.last_converted_date = get_date_modified(self.Filepath + "/" + self.last_converted)
self.last_exported_volume = self.last_exported
self.newest_volume = self.newest
self.last_downloaded_volume = self.last_downloaded
self.last_converted_volume = self.last_converted
self.last_exported_volume_date = self.last_exported_date
self.newest_volume_date = self.newest_date
self.last_downloaded_volume_date = self.last_downloaded_date
self.last_converted_volume_date = self.last_converted_date
self.last_exported_volume_name = self.last_exported
self.newest_volume_name = self.newest
self.unexported_volumes = get_unexported_volumes(self)
if __name__ == '__main__':
print("Starting")
# File Paths for Debugging purposes
Fpath = '~/'
F_Temp_path = '~/temp'
#parses directory for book based on folder names
subfolders = {'Encyclopedia': ['Vol.001', 'Vol.002', 'Vol.003', 'Vol.004', 'Vol.005'], 'Enginnering_Encyclopedia': ['Avionics', 'Civil', 'Electrical', 'Materials', 'Mechanical']}
print("Done")
#converts my dictionary of book titles and volumes into individual book objects
book_to_object(subfolders)
Notes:
In case anyone is wondering why I'm using objects instead of keeping everything in dictionaries, I need the flexibility that objects give.
Variables such as, file_paths and subfolders are dynamic and are based on what directory the user gives and what files are in that directory, for the purpose of asking the questions they have been hard coded so someone could copy and paste my code and reproduce the problem in question.

Inserting rows in workbook using win32com in python not working

I have a very specific question. The line:
expform_ws.Range("Total").Offset(-1, 0).EntireRow.Insert
in the code below is not working:
# Write data in expenses form
expform_wb = xl.Workbooks.Open(expform_path, Editable=True)
expform_ws = expform_wb.Worksheets('Expense Form')
last_row_ef = expense_items + 15
expform_ws.Range("Total").Offset(-1, 0).EntireRow.Insert
expform_ws.Range('Casecode').Value = case_code
expform_ws.Range('D6').Value = name
expform_ws.Range('D7').Value = last_name
expform_ws.Range('D8').Value = datetime.date.today().strftime("%d/%m/%Y")
expform_ws.Range('B16:B' + str(last_row_ef)).Value = date
expform_ws.Range('D16:D' + str(last_row_ef)).Value = descr
In case this helps: the line gets highlighted in PyCharm as "Statement seems to have no effect".
Anyone can help to spot what I am doing wrong?
Thanks!
In this line
expform_ws.Range("Total").Offset(-1, 0).EntireRow.Insert
You aren't actually CALLING the function, you are just getting "reference" to it, add () to call it
expform_ws.Range("Total").Offset(-1, 0).EntireRow.Insert()

Why doesn't Python want to access the second item of my 2-items list?

I'm trying to split an email address under the format jim.smith-royal#smth.edu or jim.smith#smth.edu into a name and a surname, so jim and smith, or jim and smith royal (with a space in between). (I am a beginner so I may not be doing it in the simplest way, but still).
for row in votants:
mail = row[1]
full_name = mail.split('#')[0]
prenom = full_name.split('.')[0]
#The code works until here, full_name.split gives me ['jim','smith'] and prenom gives me 'jim'
pre_name = full_name.split('.')
nom = pre_name[1]
#The problem is until here, but I kept the rest of my code for anyone who might have the same objective as me
try:
nom = nom.split('-')[0] + " " + nom.split('-')[1]
except Exception:
pass
row.append(prenom)
row.append(nom)
Instead of giving me nom as 'smith', I get "IndexError: list index out of range".
I tried:
mail = "jim.smith#smth.edu"
full_name = mail.split('#')[0]
prenom = full_name.split('.')[0]
#The code works until here, full_name.split gives me ['jim','smith'] and prenom gives me 'jim'
pre_name = full_name.split('.')
nom = pre_name[1]
#The problem is until here, but I kept the rest of my code for anyone who might have the same objective as me
print(full_name);
print(pre_name);
print(nom);
print(prenom);
and it prints:
jim.smith
['jim', 'smith']
smith
jim
Without any exceptions.
Problem:
Like comments said: If no "." is used in name (before #), you are probably facing the indexOutOfRange Exception.
Possible Solutions:
Surround it in if-else block:
if len(pre_name) >= 2
or use try-except:
try:
nom = pre_name[1]
except IndexError:
nom = pre_name[0];
or use:
if "." in full_name:
pre_name = full_name.split('.')
nom = pre_name[1]
General Debugging:
use print() earlier.
// works until here
pre_name = full_name.split('.')
print(pre_name) // if no '.' was used, you will see the array contains only 1 element
nom = pre_name[1] // problem here?

Reduce RAM usage in Python script

I've written a quick little program to scrape book data off of a UNESCO website which contains information about book translations. The code is doing what I want it to, but by the time it's processed about 20 countries, it's using ~6GB of RAM. Since there are around 200 I need to process, this isn't going to work for me.
I'm not sure where all the RAM usage is coming from, so I'm not sure how to reduce it. I'm assuming that it's the dictionary that's holding all the book information, but I'm not positive. I'm not sure if I should simply make the program run once for each country, rather than processing the lot of them? Or if there's a better way to do it?
This is the first time I've written anything like this, and I'm a pretty novice, self-taught programmer, so please point out any significant flaws in the code, or improvement tips you have that may not directly relate to the question at hand.
This is my code, thanks in advance for any assistance.
from __future__ import print_function
import urllib2, os
from bs4 import BeautifulSoup, SoupStrainer
''' Set list of countries and their code for niceness in explaining what
is actually going on as the program runs. '''
countries = {"AFG":"Afghanistan","ALA":"Aland Islands","DZA":"Algeria"}
'''List of country codes since dictionaries aren't sorted in any
way, this makes processing easier to deal with if it fails at
some point, mid run.'''
country_code_list = ["AFG","ALA","DZA"]
base_url = "http://www.unesco.org/xtrans/bsresult.aspx?lg=0&c="
destination_directory = "/Users/robbie/Test/"
only_restable = SoupStrainer(class_="restable")
class Book(object):
def set_author(self,book):
'''Parse the webpage to find author names. Finds last name, then
first name of original author(s) and sets the Book object's
Author attribute to the resulting string.'''
authors = ""
author_last_names = book.find_all('span',class_="sn_auth_name")
author_first_names = book.find_all('span', attrs={\
'class':"sn_auth_first_name"})
if author_last_names == []: self.Author = [" "]
for author in author_last_names:
try:
first_name = author_first_names.pop()
authors = authors + author.getText() + ', ' + \
first_name.getText()
except IndexError:
authors = authors + (author.getText())
self.author = authors
def set_quality(self,book):
''' Check to see if book page is using Quality, then set it if
so.'''
quality = book.find_all('span', class_="sn_auth_quality")
if len(quality) == 0: self.quality = " "
else: self.quality = quality[0].contents[0]
def set_target_title(self,book):
target_title = book.find_all('span', class_="sn_target_title")
if len(target_title) == 0: self.target_title = " "
else: self.target_title = target_title[0].contents[0]
def set_target_language(self,book):
target_language = book.find_all('span', class_="sn_target_lang")
if len(target_language) == 0: self.target_language = " "
else: self.target_language = target_language[0].contents[0]
def set_translator_name(self,book) :
translators = ""
translator_last_names = book.find_all('span', class_="sn_transl_name")
translator_first_names = book.find_all('span', \
class_="sn_transl_first_name")
if translator_first_names == [] and translator_last_names == [] :
self.translators = " "
return None
for translator in translator_last_names:
try:
first_name = translator_first_names.pop()
translators = translators + \
(translator.getText() + ',' \
+ first_name.getText())
except IndexError:
translators = translators + \
(translator.getText())
self.translators = translators
def set_published_city(self,book) :
published_city = book.find_all('span', class_="place")
if len(published_city) == 0:
self.published_city = " "
else: self.published_city = published_city[0].contents[0]
def set_publisher(self,book) :
publisher = book.find_all('span', class_="place")
if len(publisher) == 0:
self.publisher = " "
else: self.publisher = publisher[0].contents[0]
def set_published_country(self,book) :
published_country = book.find_all('span', \
class_="sn_country")
if len(published_country) == 0:
self.published_country = " "
else: self.published_country = published_country[0].contents[0]
def set_year(self,book) :
year = book.find_all('span', class_="sn_year")
if len(year) == 0:
self.year = " "
else: self.year = year[0].contents[0]
def set_pages(self,book) :
pages = book.find_all('span', class_="sn_pagination")
if len(pages) == 0:
self.pages = " "
else: self.pages = pages[0].contents[0]
def set_edition(self, book) :
edition = book.find_all('span', class_="sn_editionstat")
if len(edition) == 0:
self.edition = " "
else: self.edition = edition[0].contents[0]
def set_original_title(self,book) :
original_title = book.find_all('span', class_="sn_orig_title")
if len(original_title) == 0:
self.original_title = " "
else: self.original_title = original_title[0].contents[0]
def set_original_language(self,book) :
languages = ''
original_languages = book.find_all('span', \
class_="sn_orig_lang")
for language in original_languages:
languages = languages + language.getText() + ', '
self.original_languages = languages
def export(self, country):
''' Function to allow us to easilly pull the text from the
contents of the Book object's attributes and write them to the
country in which the book was published's CSV file.'''
file_name = os.path.join(destination_directory + country + ".csv")
with open(file_name, "a") as by_country_csv:
print(self.author.encode('UTF-8') + " & " + \
self.quality.encode('UTF-8') + " & " + \
self.target_title.encode('UTF-8') + " & " + \
self.target_language.encode('UTF-8') + " & " + \
self.translators.encode('UTF-8') + " & " + \
self.published_city.encode('UTF-8') + " & " + \
self.publisher.encode('UTF-8') + " & " + \
self.published_country.encode('UTF-8') + " & " + \
self.year.encode('UTF-8') + " & " + \
self.pages.encode('UTF-8') + " & " + \
self.edition.encode('UTF-8') + " & " + \
self.original_title.encode('UTF-8') + " & " + \
self.original_languages.encode('UTF-8'), file=by_country_csv)
by_country_csv.close()
def __init__(self, book, country):
''' Initialize the Book object by feeding it the HTML for its
row'''
self.set_author(book)
self.set_quality(book)
self.set_target_title(book)
self.set_target_language(book)
self.set_translator_name(book)
self.set_published_city(book)
self.set_publisher(book)
self.set_published_country(book)
self.set_year(book)
self.set_pages(book)
self.set_edition(book)
self.set_original_title(book)
self.set_original_language(book)
def get_all_pages(country,base_url):
''' Create a list of URLs to be crawled by adding the ISO_3166-1_alpha-3
country code to the URL and then iterating through the results every 10
pages. Returns a string.'''
base_page = urllib2.urlopen(base_url+country)
page = BeautifulSoup(base_page, parse_only=only_restable)
result_number = page.find_all('td',class_="res1",limit=1)
if not result_number:
return 0
str_result_number = str(result_number[0].getText())
results_total = int(str_result_number.split('/')[1])
page.decompose()
return results_total
def build_list(country_code_list, countries):
''' Build the list of all the books, and return a list of Book objects
in case you want to do something with them in something else, ever.'''
for country in country_code_list:
print("Processing %s now..." % countries[country])
results_total = get_all_pages(country, base_url)
for url in range(results_total):
if url % 10 == 0 :
all_books = []
target_page = urllib2.urlopen(base_url + country \
+"&fr="+str(url))
page = BeautifulSoup(target_page, parse_only=only_restable)
books = page.find_all('td',class_="res2")
for book in books:
all_books.append(Book (book,country))
page.decompose()
for title in all_books:
title.export(country)
return
if __name__ == "__main__":
build_list(country_code_list,countries)
print("Completed.")
I guess I'll just list off some of the problems or possible improvements in no particular order:
Follow PEP 8.
Right now, you've got lots of variables and functions named using camel-case like setAuthor. That's not the conventional style for Python; Python would typically named that set_author (and published_country rather than PublishedCountry, etc.). You can even change the names of some of the things you're calling: for one, BeautifulSoup supports findAll for compatibility, but find_all is recommended.
Besides naming, PEP 8 also specifies a few other things; for example, you'd want to rewrite this:
if len(resultNumber) == 0 : return 0
as this:
if len(result_number) == 0:
return 0
or even taking into account the fact that empty lists are falsy:
if not result_number:
return 0
Pass a SoupStrainer to BeautifulSoup.
The information you're looking for is probably in only part of the document; you don't need to parse the whole thing into a tree. Pass a SoupStrainer as the parse_only argument to BeautifulSoup. This should reduce memory usage by discarding unnecessary parts early.
decompose the soup when you're done with it.
Python primarily uses reference counting, so removing all circular references (as decompose does) should let its primary mechanism for garbage collection, reference counting, free up a lot of memory. Python also has a semi-traditional garbage collector to deal with circular references, but reference counting is much faster.
Don't make Book.__init__ write things to disk.
In most cases, I wouldn't expect just creating an instance of a class to write something to disk. Remove the call to export; let the user call export if they want it to be put on the disk.
Stop holding on to so much data in memory.
You're accumulating all this data into a dictionary just to export it afterwards. The obvious thing to do to reduce memory is to dump it to disk as soon as possible. Your comment indicates that you're putting it in a dictionary to be flexible; but that doesn't mean you have to collect it all in a list: use a generator, yielding items as you scrape them. Then the user can iterate over it just like a list:
for book in scrape_books():
book.export()
…but with the advantage that at most one book will be kept in memory at a time.
Use the functions in os.path rather than munging paths yourself.
Your code right now is rather fragile when it comes to path names. If I accidentally removed the trailing slash from destinationDirectory, something unintended happens. Using os.path.join prevents that from happening and deals with cross-platform differences:
>>> os.path.join("/Users/robbie/Test/", "USA")
'/Users/robbie/Test/USA'
>>> os.path.join("/Users/robbie/Test", "USA") # still works!
'/Users/robbie/Test/USA'
>>> # or say we were on Windows:
>>> os.path.join(r"C:\Documents and Settings\robbie\Test", "USA")
'C:\\Documents and Settings\\robbie\\Test\\USA'
Abbreviate attrs={"class":...} to class_=....
BeautifulSoup 4.1.2 introduces searching with class_, which removes the need for the verbose attrs={"class":...}.
I imagine there are even more things you can change, but that's quite a few to start with.
What do you want the booklist for, in the end? You should export each book at the end of the "for url in range" block (inside it), and do without the allbooks dict. If you really need a list, define exactly what infos you will need, not keeping full Book objects.

Python While Not recordset.EOF that wont .MoveNext

I don't really understand why this is happening. Maybe a fresh set of eyes could help.
in the table of an access database, say C:\dbase.mdb, I have a table called tProcedureGroups with two fields, ID and Description.
ID Description
1 DIAGNOSTIC
2 PREVENTATIVE
3 RESTORATIVE
So my recordset should be a lot more than an infinite... ID "\t" + Description + "\n"
Here's my code... this had to of happened to a few of you python gurus out there!
Thanks so much for your help, everyone on this site seems super helpful.
import win32com.client
def Procedures(listed):
DB = r"C:\dbase.mdb"
engine = win32com.client.Dispatch("DAO.DBEngine.36")
db = engine.OpenDatabase(DB)
sql = "select * from [tProcedureGroups]"
access = db.OpenRecordset(sql)
while not access.EOF:
for i in listed:
print i + '\t' + str(access.Fields(i).value) + '\n'
access.MoveNext
fields = ["ID", "Description"]
get_procs = Procedures(fields)
In Python you need to call methods explicitly with ().
So change:
access.MoveNext
to
access.MoveNext()

Categories