""" csv.py - read/write/investigate CSV files """ import re from _csv import Error, __version__, writer, reader, register_dialect, \ unregister_dialect, get_dialect, list_dialects, \ field_size_limit, \ QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE, \ __doc__ from _csv import Dialect as _Dialect from io import StringIO __all__ = [ "QUOTE_MINIMAL", "QUOTE_ALL", "QUOTE_NONNUMERIC", "QUOTE_NONE", "Error", "Dialect", "__doc__", "excel", "excel_tab", "field_size_limit", "reader", "writer", "register_dialect", "get_dialect", "list_dialects", "Sniffer", "unregister_dialect", "__version__", "DictReader", "DictWriter" ] class Dialect: """Describe a CSV dialect. This must be subclassed (see csv.excel). Valid attributes are: delimiter, quotechar, escapechar, doublequote, skipinitialspace, lineterminator, quoting. """ _name = "" _valid = False # placeholders delimiter = None quotechar = None escapechar = None doublequote = None skipinitialspace = None lineterminator = None quoting = None def __init__(self): if self.__class__ != Dialect: self._valid = True self._validate() def _validate(self): try: _Dialect(self) except TypeError as e: # We do this for compatibility with py2.3 raise Error(str(e)) class excel(Dialect): """Describe the usual properties of Excel-generated CSV files.""" delimiter = ',' quotechar = '"' doublequote = True skipinitialspace = False lineterminator = '\r\n' quoting = QUOTE_MINIMAL register_dialect("excel", excel) class excel_tab(excel): """Describe the usual properties of Excel-generated TAB-delimited files.""" delimiter = '\t' register_dialect("excel-tab", excel_tab) class unix_dialect(Dialect): """Describe the usual properties of Unix-generated CSV files.""" delimiter = ',' quotechar = '"' doublequote = True skipinitialspace = False lineterminator = '\n' quoting = QUOTE_ALL register_dialect("unix", unix_dialect) class DictReader: def __init__(self, f, fieldnames=None, restkey=None, restval=None, dialect="excel", *args, **kwds): self._fieldnames = fieldnames # list of keys for the dict self.restkey = restkey # key to catch long rows self.restval = restval # default value for short rows self.reader = reader(f, dialect, *args, **kwds) self.dialect = dialect self.line_num = 0 def __iter__(self): return self @property def fieldnames(self): if self._fieldnames is None: try: self._fieldnames = next(self.reader) except StopIteration: pass self.line_num = self.reader.line_num return self._fieldnames @fieldnames.setter def fieldnames(self, value): self._fieldnames = value def __next__(self): if self.line_num == 0: # Used only for its side effect. self.fieldnames row = next(self.reader) self.line_num = self.reader.line_num # unlike the basic reader, we prefer not to return blanks, # because we will typically wind up with a dict full of None # values while row == []: row = next(self.reader) d = dict(zip(self.fieldnames, row)) lf = len(self.fieldnames) lr = len(row) if lf < lr: d[self.restkey] = row[lf:] elif lf > lr: for key in self.fieldnames[lr:]: d[key] = self.restval return d class DictWriter: def __init__(self, f, fieldnames, restval="", extrasaction="raise", dialect="excel", *args, **kwds): self.fieldnames = fieldnames # list of keys for the dict self.restval = restval # for writing short dicts if extrasaction.lower() not in ("raise", "ignore"): raise ValueError("extrasaction (%s) must be 'raise' or 'ignore'" % extrasaction) self.extrasaction = extrasaction self.writer = writer(f, dialect, *args, **kwds) def writeheader(self): header = dict(zip(self.fieldnames, self.fieldnames)) self.writerow(header) def _dict_to_list(self, rowdict): if self.extrasaction == "raise": wrong_fields = [k for k in rowdict if k not in self.fieldnames] if wrong_fields: raise ValueError("dict contains fields not in fieldnames: " + ", ".join([repr(x) for x in wrong_fields])) return (rowdict.get(key, self.restval) for key in self.fieldnames) def writerow(self, rowdict): return self.writer.writerow(self._dict_to_list(rowdict)) def writerows(self, rowdicts): return self.writer.writerows(map(self._dict_to_list, rowdicts)) # Guard Sniffer's type checking against builds that exclude complex() try: complex except NameError: complex = float class Sniffer: ''' "Sniffs" the format of a CSV file (i.e. delimiter, quotechar) Returns a Dialect object. ''' def __init__(self): # in case there is more than one possible delimiter self.preferred = [',', '\t', ';', ' ', ':'] def sniff(self, sample, delimiters=None): """ Returns a dialect (or None) corresponding to the sample """ quotechar, doublequote, delimiter, skipinitialspace = \ self._guess_quote_and_delimiter(sample, delimiters) if not delimiter: delimiter, skipinitialspace = self._guess_delimiter(sample, delimiters) if not delimiter: raise Error("Could not determine delimiter") class dialect(Dialect): _name = "sniffed" lineterminator = '\r\n' quoting = QUOTE_MINIMAL # escapechar = '' dialect.doublequote = doublequote dialect.delimiter = delimiter # _csv.reader won't accept a quotechar of '' dialect.quotechar = quotechar or '"' dialect.skipinitialspace = skipinitialspace return dialect def _guess_quote_and_delimiter(self, data, delimiters): """ Looks for text enclosed between two identical quotes (the probable quotechar) which are preceded and followed by the same character (the probable delimiter). For example: ,'some text', The quote with the most wins, same with the delimiter. If there is no quotechar the delimiter can't be determined this way. """ matches = [] for restr in ('(?P<delim>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?P=delim)', # ,".*?", '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?P<delim>[^\w\n"\'])(?P<space> ?)', # ".*?", '(?P<delim>>[^\w\n"\'])(?P<space> ?)(?P<quote>["\']).*?(?P=quote)(?:$|\n)', # ,".*?" '(?:^|\n)(?P<quote>["\']).*?(?P=quote)(?:$|\n)'): # ".*?" (no delim, no space) regexp = re.compile(restr, re.DOTALL | re.MULTILINE) matches = regexp.findall(data) if matches: break if not matches: # (quotechar, doublequote, delimiter, skipinitialspace) return ('', False, None, 0) quotes = {} delims = {} spaces = 0 groupindex = regexp.groupindex for m in matches: n = groupindex['quote'] - 1 key = m[n] if key: quotes[key] = quotes.get(key, 0) + 1 try: n = groupindex['delim'] - 1 key = m[n] except KeyError: continue if key and (delimiters is None or key in delimiters): delims[key] = delims.get(key, 0) + 1 try: n = groupindex['space'] - 1 except KeyError: continue if m[n]: spaces += 1 quotechar = max(quotes, key=quotes.get) if delims: delim = max(delims, key=delims.get) skipinitialspace = delims[delim] == spaces if delim == '\n': # most likely a file with a single column delim = '' else: # there is *no* delimiter, it's a single column of quoted data delim = '' skipinitialspace = 0 # if we see an extra quote between delimiters, we've got a # double quoted format dq_regexp = re.compile( r"((%(delim)s)|^)\W*%(quote)s[^%(delim)s\n]*%(quote)s[^%(delim)s\n]*%(quote)s\W*((%(delim)s)|$)" % \ {'delim':re.escape(delim), 'quote':quotechar}, re.MULTILINE) if dq_regexp.search(data): doublequote = True else: doublequote = False return (quotechar, doublequote, delim, skipinitialspace) def _guess_delimiter(self, data, delimiters): """ The delimiter /should/ occur the same number of times on each row. However, due to malformed data, it may not. We don't want an all or nothing approach, so we allow for small variations in this number. 1) build a table of the frequency of each character on every line. 2) build a table of frequencies of this frequency (meta-frequency?), e.g. 'x occurred 5 times in 10 rows, 6 times in 1000 rows, 7 times in 2 rows' 3) use the mode of the meta-frequency to determine the /expected/ frequency for that character 4) find out how often the character actually meets that goal 5) the character that best meets its goal is the delimiter For performance reasons, the data is evaluated in chunks, so it can try and evaluate the smallest portion of the data possible, evaluating additional chunks as necessary. """ data = list(filter(None, data.split('\n'))) ascii = [chr(c) for c in range(127)] # 7-bit ASCII # build frequency tables chunkLength = min(10, len(data)) iteration = 0 charFrequency = {} modes = {} delims = {} start, end = 0, min(chunkLength, len(data)) while start < len(data): iteration += 1 for line in data[start:end]: for char in ascii: metaFrequency = charFrequency.get(char, {}) # must count even if frequency is 0 freq = line.count(char) # value is the mode metaFrequency[freq] = metaFrequency.get(freq, 0) + 1 charFrequency[char] = metaFrequency for char in charFrequency.keys(): items = list(charFrequency[char].items()) if len(items) == 1 and items[0][0] == 0: continue # get the mode of the frequencies if len(items) > 1: modes[char] = max(items, key=lambda x: x[1]) # adjust the mode - subtract the sum of all # other frequencies items.remove(modes[char]) modes[char] = (modes[char][0], modes[char][1] - sum(item[1] for item in items)) else: modes[char] = items[0] # build a list of possible delimiters modeList = modes.items() total = float(chunkLength * iteration) # (rows of consistent data) / (number of rows) = 100% consistency = 1.0 # minimum consistency threshold threshold = 0.9 while len(delims) == 0 and consistency >= threshold: for k, v in modeList: if v[0] > 0 and v[1] > 0: if ((v[1]/total) >= consistency and (delimiters is None or k in delimiters)): delims[k] = v consistency -= 0.01 if len(delims) == 1: delim = list(delims.keys())[0] skipinitialspace = (data[0].count(delim) == data[0].count("%c " % delim)) return (delim, skipinitialspace) # analyze another chunkLength lines start = end end += chunkLength if not delims: return ('', 0) # if there's more than one, fall back to a 'preferred' list if len(delims) > 1: for d in self.preferred: if d in delims.keys(): skipinitialspace = (data[0].count(d) == data[0].count("%c " % d)) return (d, skipinitialspace) # nothing else indicates a preference, pick the character that # dominates(?) items = [(v,k) for (k,v) in delims.items()] items.sort() delim = items[-1][1] skipinitialspace = (data[0].count(delim) == data[0].count("%c " % delim)) return (delim, skipinitialspace) def has_header(self, sample): # Creates a dictionary of types of data in each column. If any # column is of a single type (say, integers), *except* for the first # row, then the first row is presumed to be labels. If the type # can't be determined, it is assumed to be a string in which case # the length of the string is the determining factor: if all of the # rows except for the first are the same length, it's a header. # Finally, a 'vote' is taken at the end for each column, adding or # subtracting from the likelihood of the first row being a header. rdr = reader(StringIO(sample), self.sniff(sample)) header = next(rdr) # assume first row is header columns = len(header) columnTypes = {} for i in range(columns): columnTypes[i] = None checked = 0 for row in rdr: # arbitrary number of rows to check, to keep it sane if checked > 20: break checked += 1 if len(row) != columns: continue # skip rows that have irregular number of columns for col in list(columnTypes.keys()): for thisType in [int, float, complex]: try: thisType(row[col]) break except (ValueError, OverflowError): pass else: # fallback to length of string thisType = len(row[col]) if thisType != columnTypes[col]: if columnTypes[col] is None: # add new column type columnTypes[col] = thisType else: # type is inconsistent, remove column from # consideration del columnTypes[col] # finally, compare results against first row and "vote" # on whether it's a header hasHeader = 0 for col, colType in columnTypes.items(): if type(colType) == type(0): # it's a length if len(header[col]) != colType: hasHeader += 1 else: hasHeader -= 1 else: # attempt typecast try: colType(header[col]) except (ValueError, TypeError): hasHeader += 1 else: hasHeader -= 1 return hasHeader > 0

RE-INVENTING THE TELEVISION NEWS BUSINESS*

A revolution in video storytelling

Creating entirely new & cost-effective production methods

From the world leaders in video production training and the creators of Character Driven Storytelling™

*and every other business that uses video

WHAT WE DO

Over the past 35 years, we have designed, built or restructured some of the most powerful news and journalism companies in the world.

We replace the traditional TV news ‘crew’ with one highly trained journalist, working alone with nothing but an iPhone.

No more TV news ‘crews’, no editors and no field producers.

This is television news done the way newspaper journalism is done – one reporter with their electronic pad and pencil.

In doing this, we can cut the cost of production by as much as 75% while increasing ratings and audience engagement.

In the place of conventional TV news ‘packages’ – ie, reporter stand up, interview, b-roll, man on the street, we marry great journalism with Netflix and Hollywood storytelling.

It’s a combination that works.

We have taken most of our clients to #1 in their respective markets.

And it’s not just for news. Any company, any profit, any NGO and anyone else who is online needs to tell their story in compelling yet cost-effective video. We can teach you to do that. Either in person or virtually.

EXAMPLES OF WHAT WE CAN TEACH YOUR STAFF TO PRODUCE

ITAY HOD

Itay Hod, MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2018.

Because he works alone, with only an iPhone, he was able to embed himself with a homeless family.

Here’s the story he produced in a one-day turn.

KIET DO

Kiet Do, an MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2021.

Here is a story he produced, all on his own, with only an iPhone and in a one-day turn.

TAYLOR SCHAUB

Taylor Schaub, an MMJ with Spectrum News 1 in LA, took the 5-Day Intensive Video Storytelling Bootcamp in 2023.

Here is a story he turned in only one day, using only an iPhone. It was the first video story he ever did and it was nominated for an Emmy.

THE BOOTCAMP

How do we convert stations and whole networks to working in this way?

Since 1988, we have run intensive 5-Day Video Storytelling Bootcamps

We have done these all over the world.

These are hands-on bootcamps, and participants learn an entirely new way of creating TV news stories.

-We shoot at a 3:1 ratio or lower, so turnaround times are fast.

-We go directly from camera to timelilne and edit – no written scripts. We work in the medium of pictures and sound.

-We are entirely character-driven.

-We are driven by pictures and real events.

-We are focused almost entirely on ’the viewer experience’.

Since 1988, more than 70,000 journalists around the world have taken our bootcamps, either in person on virtualy.

Case Studies

CBS News

We have started to work with CBS News, bringing our ideas of character-driven storytelling to one of the most successful and biggest networks in the United States. Since beginning to work with them ratings have climbed and more importantly, audience engagement is through the ceiling.

Learn More

New York Times Television

We started New York Times Television in 1990 and it was the first paper to be brought into the world of TV. It quickly became one of the most successful non-fiction production companies in the United States. The series and documentaries we produced won many awards including multiple Emmys.

Learn More

The BBC

We have been working with the BBC since the year 2000 helping to convert their national news network to our visual storytelling technique. Most recently we have trained teams from their sports, documentaries, and comedy divisions to make character-driven stories using only smartphones.

Learn More

Spectrum News

For the past five years we have worked with Spectrum News to introduce and train their journalists on visual, character driven storytelling using smartphones helping to create a different kind of local news for their network of 24-Hour News Stations across the United States.

Learn More

The United Nations

In 2006, we were approached by the United Nations. Rather than rely on news outlets, it would be much easier to train the field operatives to produce their own stories. We spent two years working with the UN, training more than 100 of their staff in bootcamps in Geneva and Nairobi.

Learn More

The Newark Star-Ledger

We trained 50 print reporters at the paper to shoot and tell their own stories, in conjunction with their print work. We built a TV newsroom in their existing print newsroom – you could not ask for a better set and they began to live stream their stories in conjunction with their print work.

Learn More

Mcgraw Hill

We spent two years with McGraw Hill, training more than 150 of their staffers, making them completely video literate. McGraw/Hill media properties we transit included Business Week, Aviation Week, (what was the name of the architecture magazine), and JD Power and Associates.

Learn More

Voice of America

In 1990, we were approached by The Voice of America, the official broadcasting agency for the United States Government. When we met with VOA, they were only a short wave radio broadcaster, but working with them, we took them into television, launching VOA-TV.

Learn More

Oyster Yachts

British based Oyster Yachts makes some of the finest yachts in the world. Like every other company, they had to find a way to feed the never-ending video demands of social media – sites like Instagram and TikTok. We trained the Oyster staff to tell their own stories, using only iPhones.

Learn More

Scottish Environmental Protection Agency

We were approached by SEPA, the Scottish Environmental Protection Agency because they had to continually find a way to ‘feed the media beast’. The result was that SEPA was able to tell their own stories, whenever they wanted, and at almost no additional cost.

Learn More

Michael on Media

Michael Rosenblum has been writing about the media since 1988. His work and ideas have appeared in The Guardian, The Huffington Post, Ilkeston Life and many other publications.

He has been blogging regularly for the past 35 years on this subject. Having taught media studies at Columbia University, NYU and now the University of Oxford, he is considered an expert on this subject.

Continue reading this post or look back at previous posts.

Do You Have Questions About Learning Video Skills?

If you would like to know more about our courses contact us and one of our training advisors will be happy to call you.

Your IP : 216.73.216.134

RE-INVENTING THE TELEVISION NEWS BUSINESS*

A revolution in video storytelling

Creating entirely new & cost-effective production methods

From the world leaders in video production training and the creators of Character Driven Storytelling™

*and every other business that uses video

WHAT WE DO

Over the past 35 years, we have designed, built or restructured some of the most powerful news and journalism companies in the world.

We replace the traditional TV news ‘crew’ with one highly trained journalist, working alone with nothing but an iPhone.

No more TV news ‘crews’, no editors and no field producers.

This is television news done the way newspaper journalism is done – one reporter with their electronic pad and pencil.

In doing this, we can cut the cost of production by as much as 75% while increasing ratings and audience engagement.

In the place of conventional TV news ‘packages’ – ie, reporter stand up, interview, b-roll, man on the street, we marry great journalism with Netflix and Hollywood storytelling.

It’s a combination that works.

We have taken most of our clients to #1 in their respective markets.

And it’s not just for news. Any company, any profit, any NGO and anyone else who is online needs to tell their story in compelling yet cost-effective video. We can teach you to do that. Either in person or virtually.

EXAMPLES OF WHAT WE CAN TEACH YOUR STAFF TO PRODUCE

ITAY HOD

Itay Hod, MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2018.

Because he works alone, with only an iPhone, he was able to embed himself with a homeless family.

Here’s the story he produced in a one-day turn.

KIET DO

Kiet Do, an MMJ with KPIX/CBS in San Francisco, took the 5-Day Intensive Video Storytelling Bootcamp in 2021.

Here is a story he produced, all on his own, with only an iPhone and in a one-day turn.

TAYLOR SCHAUB

Taylor Schaub, an MMJ with Spectrum News 1 in LA, took the 5-Day Intensive Video Storytelling Bootcamp in 2023.

Here is a story he turned in only one day, using only an iPhone. It was the first video story he ever did and it was nominated for an Emmy.

THE BOOTCAMP

How do we convert stations and whole networks to working in this way?

Since 1988, we have run intensive 5-Day Video Storytelling Bootcamps

We have done these all over the world.

These are hands-on bootcamps, and participants learn an entirely new way of creating TV news stories.

-We shoot at a 3:1 ratio or lower, so turnaround times are fast.

-We go directly from camera to timelilne and edit – no written scripts. We work in the medium of pictures and sound.

-We are entirely character-driven.

-We are driven by pictures and real events.

-We are focused almost entirely on ’the viewer experience’.

Since 1988, more than 70,000 journalists around the world have taken our bootcamps, either in person on virtualy.

Case Studies

CBS News

New York Times Television

The BBC

Spectrum News

The United Nations

The Newark Star-Ledger

Mcgraw Hill

Voice of America

Oyster Yachts

Scottish Environmental Protection Agency

Michael on Media