コード例 #1
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
    def run(self):
        pages = WikiPage.all()
        pages.filter('unit', self.unit)
        page_iter = pages.run()

        ct = CrossTab()
        vals_by_field = defaultdict(set)
        fields = [field.name for field in forms[self.unit]() if isinstance(field, BaseRankingField)]

        for page in page_iter:
            author = page.author
            ranks = {'group_id': author.group_id}
            # want to tabulate: 
            #   ranks of each item: dogs=1, cats=2, bunnies=3
            #   networking group of the student
            for field in fields:
                value = getattr(page, field)
                if not value:
                    continue
                for r in value:
                    vals_by_field[field].add(r)
                ranks.update((item, n) for n, item in enumerate(value, start=1))
            ct.add(**ranks)

        for field, values in vals_by_field.iteritems():
            yield dict(zip(self.fields, [field]))
            for v in values:
                for row in ct.table(v, 'group_id'):
                    yield dict(zip(self.fields, row))
                yield {}
コード例 #2
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
    def run(self):
        pages = WikiPage.all()
        pages.filter('unit', self.unit)
        page_iter = pages.run()

        ct = CrossTab()
        vals_by_field = defaultdict(set)
        fields = [
            field.name for field in forms[self.unit]()
            if isinstance(field, BaseRankingField)
        ]

        for page in page_iter:
            author = page.author
            ranks = {'group_id': author.group_id}
            # want to tabulate:
            #   ranks of each item: dogs=1, cats=2, bunnies=3
            #   networking group of the student
            for field in fields:
                value = getattr(page, field)
                if not value:
                    continue
                for r in value:
                    vals_by_field[field].add(r)
                ranks.update(
                    (item, n) for n, item in enumerate(value, start=1))
            ct.add(**ranks)

        for field, values in vals_by_field.iteritems():
            yield dict(zip(self.fields, [field]))
            for v in values:
                for row in ct.table(v, 'group_id'):
                    yield dict(zip(self.fields, row))
                yield {}
コード例 #3
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
class CommentCountQuery(TableMakerMapper):
    KIND = WikiComment
    FIELDS = [ 'c%d' % n for n in range(40) ]

    def __init__(self, **kwargs):
        TableMakerMapper.__init__(self)
        self.tab = CrossTab()
        self.word_tab = CrossTab()
        self.names = {}

    _re_word_boundaries = re.compile(r'\b')
    def num_words(self, string):
        return len(self._re_word_boundaries.findall(string)) >> 1


    def map(self, comment):
        email = comment.author_email
        if email not in self.names:
            self.names[email] = comment.author.name
        unit = comment.topic.unit
        if unit is None:
            unit = 'Profile'
        self.tab.add(email=email, comments_in_unit=unit)
        comment_text = Markup(comment.text).striptags()
        self.word_tab.add_count(
                self.num_words(comment_text),
                email=email, words_in_unit=unit)
        return ([], [])

    def finish(self):
        for comments_row, words_row in itertools.izip(
                self.tab.table('email', 'comments_in_unit'),
                self.word_tab.table('email', 'words_in_unit')):
            blank_or_email = comments_row[0]

            if ':' in blank_or_email:
                blank_or_email = blank_or_email.split(':', 1)[1]

            name = self.names.get(blank_or_email, '')

            row = [name, blank_or_email]
            for comment_cell, word_cell in zip(
                    comments_row[1:], words_row[1:]):
                row.extend([comment_cell, word_cell])

            self.add_row(dict(zip(self.FIELDS, row)))
コード例 #4
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
class CommentCountQuery(TableMakerMapper):
    KIND = WikiComment
    FIELDS = ['c%d' % n for n in range(40)]

    def __init__(self, **kwargs):
        TableMakerMapper.__init__(self)
        self.tab = CrossTab()
        self.word_tab = CrossTab()
        self.names = {}

    _re_word_boundaries = re.compile(r'\b')

    def num_words(self, string):
        return len(self._re_word_boundaries.findall(string)) >> 1

    def map(self, comment):
        email = comment.author_email
        if email not in self.names:
            self.names[email] = comment.author.name
        unit = comment.topic.unit
        if unit is None:
            unit = 'Profile'
        self.tab.add(email=email, comments_in_unit=unit)
        comment_text = Markup(comment.text).striptags()
        self.word_tab.add_count(self.num_words(comment_text),
                                email=email,
                                words_in_unit=unit)
        return ([], [])

    def finish(self):
        for comments_row, words_row in itertools.izip(
                self.tab.table('email', 'comments_in_unit'),
                self.word_tab.table('email', 'words_in_unit')):
            blank_or_email = comments_row[0]

            if ':' in blank_or_email:
                blank_or_email = blank_or_email.split(':', 1)[1]

            name = self.names.get(blank_or_email, '')

            row = [name, blank_or_email]
            for comment_cell, word_cell in zip(comments_row[1:],
                                               words_row[1:]):
                row.extend([comment_cell, word_cell])

            self.add_row(dict(zip(self.FIELDS, row)))
コード例 #5
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
class FixedUnitRankingQuery(TableMakerMapper):
    FIELDS = ['c%d' % n for n in xrange(30)]

    KIND = WikiPage
    FILTERS = []

    def __init__(self, **kwargs):
        self.unit = kwargs['unit']
        if not self.unit:
            raise ValueError('"unit" parameter is required for this query')
        self.FILTERS = [('unit', self.unit)]
        self.ct = CrossTab()
        self.vals_by_field = defaultdict(set)
        self.ranking_fields = [
            field.name for field in forms[self.unit]()
            if isinstance(field, BaseRankingField)
        ]
        super(FixedUnitRankingQuery, self).__init__()

    def map(self, page):
        author = page.author
        # want to tabulate:
        #   ranks of each item: dogs=1, cats=2, bunnies=3
        #   networking group of the student
        for field in self.ranking_fields:
            ranks = {'group_id': author.group_id}
            value = getattr(page, field)
            if not value:
                continue
            for r in value:
                self.vals_by_field[field].add(r)
            ranks.update((item, n) for n, item in enumerate(value, start=1))
            self.ct.add(**ranks)

    def finish(self):
        # go over each field of the page
        for field, values in self.vals_by_field.iteritems():
            self.add_row(dict(zip(self.FIELDS, [field])))
            # Go over each value, giving its rankings
            for v in values:
                for row in self.ct.table(v, 'group_id'):
                    self.add_row(dict(zip(self.FIELDS, row)))
                self.add_row({})
コード例 #6
0
ファイル: student_csv.py プロジェクト: twiffy/eabooc
class FixedUnitRankingQuery(TableMakerMapper):
    FIELDS = ['c%d' % n for n in xrange(30)]

    KIND = WikiPage
    FILTERS = []

    def __init__(self, **kwargs):
        self.unit = kwargs['unit']
        if not self.unit:
            raise ValueError('"unit" parameter is required for this query')
        self.FILTERS = [('unit', self.unit)]
        self.ct = CrossTab()
        self.vals_by_field = defaultdict(set)
        self.ranking_fields = [field.name for field in forms[self.unit]() if isinstance(field, BaseRankingField)]
        super(FixedUnitRankingQuery, self).__init__()

    def map(self, page):
        author = page.author
        # want to tabulate:
        #   ranks of each item: dogs=1, cats=2, bunnies=3
        #   networking group of the student
        for field in self.ranking_fields:
            ranks = {'group_id': author.group_id}
            value = getattr(page, field)
            if not value:
                continue
            for r in value:
                self.vals_by_field[field].add(r)
            ranks.update((item, n) for n, item in enumerate(value, start=1))
            self.ct.add(**ranks)

    def finish(self):
        # go over each field of the page
        for field, values in self.vals_by_field.iteritems():
            self.add_row(dict(zip(self.FIELDS, [field])))
            # Go over each value, giving its rankings
            for v in values:
                for row in self.ct.table(v, 'group_id'):
                    self.add_row(dict(zip(self.FIELDS, row)))
                self.add_row({})