wordcloud.py 12.7 KB
Newer Older
1
2
3
4
5
6
# Author: Andreas Christian Mueller <amueller@ais.uni-bonn.de>
# (c) 2012
# Modified by: Paul Nechifor <paul@nechifor.net>
#
# License: MIT

7
from random import Random
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
import os
import re
import numpy as np
from operator import itemgetter

from PIL import Image
from PIL import ImageDraw
from PIL import ImageFont
from query_integral_image import query_integral_image

item1 = itemgetter(1)

FONT_PATH = "/usr/share/fonts/truetype/droid/DroidSansMono.ttf"
STOPWORDS = set([x.strip() for x in open(os.path.join(os.path.dirname(__file__),
                                                      'stopwords')).read().split('\n')])


def random_color_func(word, font_size, position, orientation, random_state=None):
    if random_state is None:
27
        random_state = Random()
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
    return "hsl(%d, 80%%, 50%%)" % random_state.randint(0, 255)


class WordCloud(object):
    """Word cloud object for generating and drawing.

    Parameters
    ----------
    font_path : string
        Font path to the font that will be used (OTF or TTF).
        Defaults to DroidSansMono path, but you might not have it.

    width : int (default=400)
        Width of the canvas.

    height : int (default=200)
        Height of the canvas.

    ranks_only : boolean (default=False)
        Only use the rank of the words, not the actual counts.

Andreas Mueller's avatar
Andreas Mueller committed
49
    prefer_horizontal : float (default=0.90)
50
51
52
        The ratio of times to try horizontal fitting as opposed to vertical.

    mask : nd-array or None (default=None)
53
54
55
56
        If not None, gives a binary mask on where to draw words. All zero
        entries will be considered "free" to draw on, while all non-zero
        entries will be deemed occupied. If mask is not None, width and height will be
        ignored and the shape of mask will be used instead.
57

Andreas Mueller's avatar
Andreas Mueller committed
58
    max_words : number (default=200)
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
        The maximum number of words.

    stopwords : set of strings
        The words that will be eliminated.

    Attributes
    ----------
    words_ : list of tuples (string, float)
        Word tokens with associated frequency.

    layout_ : list of tuples (string, int, (int, int), int, color))
        Encodes the fitted word cloud. Encodes for each word the string, font
        size, position, orientation and color.
    """

    def __init__(self, font_path=None, width=400, height=200, margin=5,
Andreas Mueller's avatar
Andreas Mueller committed
75
                 ranks_only=False, prefer_horizontal=0.9, mask=None, scale=1,
76
                 color_func=random_color_func, max_words=200, stopwords=None, random_state=None):
77
78
79
80
81
82
83
84
        if stopwords is None:
            stopwords = STOPWORDS
        if font_path is None:
            font_path = FONT_PATH
        self.font_path = font_path
        self.width = width
        self.height = height
        self.margin = margin
Andreas Mueller's avatar
Andreas Mueller committed
85
        self.ranks_only = ranks_only
86
87
88
89
        self.prefer_horizontal = prefer_horizontal
        self.mask = mask
        self.scale = scale
        self.color_func = color_func
Andreas Mueller's avatar
Andreas Mueller committed
90
91
        self.max_words = max_words
        self.stopwords = stopwords
92
93
94
        if isinstance(random_state, int):
            random_state = Random(random_state)
        self.random_state = random_state
95

96
    def _fit_words(self, words):
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
        """Generate the positions for words.

        Parameters
        ----------
        words : array of tuples
            A tuple contains the word and its frequency.

        Returns
        -------
        layout_ : list of tuples (string, int, (int, int), int, color))
            Encodes the fitted word cloud. Encodes for each word the string, font
            size, position, orientation and color.

        Notes
        -----
        Larger canvases with make the code significantly slower. If you need a large
        word cloud, run this function with a lower canvas size, and draw it with a
        larger scale.

        In the current form it actually just uses the rank of the counts, i.e. the
        relative differences don't matter. Play with setting the font_size in the
        main loop for different styles.
        """
120
121
122
123
        if self.random_state is not None:
            random_state = self.random_state
        else:
            random_state = Random()
124
125
126
127
128
129
130
131
132
133
134

        if len(words) <= 0:
            print("We need at least 1 word to plot a word cloud, got %d."
                  % len(words))

        if self.mask is not None:
            width = self.mask.shape[1]
            height = self.mask.shape[0]
            # the order of the cumsum's is important for speed ?!
            integral = np.cumsum(np.cumsum(self.mask, axis=1), axis=0).astype(np.uint32)
        else:
Andreas Mueller's avatar
Andreas Mueller committed
135
            height, width = self.height, self.width
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
            integral = np.zeros((height, width), dtype=np.uint32)

        # create image
        img_grey = Image.new("L", (width, height))
        draw = ImageDraw.Draw(img_grey)
        img_array = np.asarray(img_grey)
        font_sizes, positions, orientations, colors = [], [], [], []

        # intitiallize font size "large enough"
        font_size = height

        # start drawing grey image
        for word, count in words:
            # alternative way to set the font size
            if not self.ranks_only:
                font_size = min(font_size, int(100 * np.log(count + 100)))
            while True:
                # try to find a position
                font = ImageFont.truetype(self.font_path, font_size)
                # transpose font optionally
156
                if random_state.random() < self.prefer_horizontal:
157
158
159
160
161
162
163
164
165
166
                    orientation = None
                else:
                    orientation = Image.ROTATE_90
                transposed_font = ImageFont.TransposedFont(font,
                                                           orientation=orientation)
                draw.setfont(transposed_font)
                # get size of resulting text
                box_size = draw.textsize(word)
                # find possible places using integral image:
                result = query_integral_image(integral, box_size[1] + self.margin,
167
                                              box_size[0] + self.margin, random_state)
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
                if result is not None or font_size == 0:
                    break
                # if we didn't find a place, make font smaller
                font_size -= 1

            if font_size == 0:
                # we were unable to draw any more
                break

            x, y = np.array(result) + self.margin // 2
            # actually draw the text
            draw.text((y, x), word, fill="white")
            positions.append((x, y))
            orientations.append(orientation)
            font_sizes.append(font_size)
183
184
            colors.append(self.color_func(word, font_size, (x, y), orientation,
                                          random_state=random_state))
185
            # recompute integral image
Andreas Mueller's avatar
Andreas Mueller committed
186
187
188
189
            if self.mask is None:
                img_array = np.asarray(img_grey)
            else:
                img_array = np.asarray(img_grey) + self.mask
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
            # recompute bottom right
            # the order of the cumsum's is important for speed ?!
            partial_integral = np.cumsum(np.cumsum(img_array[x:, y:], axis=1),
                                         axis=0)
            # paste recomputed part into old image
            # if x or y is zero it is a bit annoying
            if x > 0:
                if y > 0:
                    partial_integral += (integral[x - 1, y:]
                                         - integral[x - 1, y - 1])
                else:
                    partial_integral += integral[x - 1, y:]
            if y > 0:
                partial_integral += integral[x:, y - 1][:, np.newaxis]

            integral[x:, y:] = partial_integral

        self.layout_ = zip(words, font_sizes, positions, orientations, colors)
        return self.layout_

210
    def _process_text(self, text):
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
        """Splits a long text into words, eliminates the stopwords.

        Parameters
        ----------
        text : string
            The text to be processed.

        Returns
        -------
        words : list of tuples (string, float)
            Word tokens with associated frequency.


        Notes
        -----
        There are better ways to do word tokenization, but I don't want to
        include all those things.
        """

        d = {}
        flags = re.UNICODE if type(text) is unicode else 0
        for word in re.findall(r"\w[\w']*", text, flags=flags):
            if word.isdigit():
                continue

            word_lower = word.lower()
            if word_lower in self.stopwords:
                continue

            # Look in lowercase dict.
            if word_lower in d:
                d2 = d[word_lower]
            else:
                d2 = {}
                d[word_lower] = d2

            # Look in any case dict.
            d2[word] = d2.get(word, 0) + 1

        d3 = {}
        for d2 in d.values():
            # Get the most popular case.
            first = max(d2.iteritems(), key=item1)[0]
            d3[first] = sum(d2.values())

        # merge plurals into the singular count (simple cases only)
        for key in d3.keys():
            if key.endswith('s'):
                key_singular = key[:-1]
                if key_singular in d3:
                    val_plural = d3[key]
                    val_singular = d3[key_singular]
                    d3[key_singular] = val_singular + val_plural
                    del d3[key]

        words = sorted(d3.iteritems(), key=item1, reverse=True)
Andreas Mueller's avatar
Andreas Mueller committed
267
        words = words[:self.max_words]
268
269
270
271
272
273
274
275
276
        maximum = float(max(d3.values()))
        for i, (word, count) in enumerate(words):
            words[i] = word, count / maximum

        self.words_ = words

        return words

    def generate(self, text):
277
278
279
        """Generate wordcloud from text.

        Calls _process_text and _fit_words.
280
281
282
283
284

        Returns
        -------
        self
        """
285
286
        self._process_text(text)
        self._fit_words(self.words_)
287
288
        return self

289
290
    def _check_generated(self):
        """Check if layout_ was computed, otherwise raise error."""
291
292
        if not hasattr(self, "layout_"):
            raise ValueError("WordCloud has not been calculated, call generate first.")
293
294
295
296
297
298
299
300
301
302

    def to_image(self):
        self._check_generated()
        if self.mask is not None:
            width = self.mask.shape[1]
            height = self.mask.shape[0]
        else:
            height, width = self.height, self.width

        img = Image.new("RGB", (width * self.scale, height * self.scale))
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
        draw = ImageDraw.Draw(img)
        for (word, count), font_size, position, orientation, color in self.layout_:
            font = ImageFont.truetype(self.font_path, font_size * self.scale)
            transposed_font = ImageFont.TransposedFont(font,
                                                       orientation=orientation)
            draw.setfont(transposed_font)
            pos = (position[1] * self.scale, position[0] * self.scale)
            draw.text(pos, word, fill=color)
        return img

    def recolor(self, random_state=None, color_func=None):
        """Recolor existing layout.

        Applying a new coloring is much faster than generating the whole wordcloud.

        Parameters
        ----------
320
321
322
        random_state : RandomState, int, or None, default=None
            If not None, a fixed random state is used. If an int is given, this
            is used as seed for a random.Random state.
323
324
325
326
327
328
329
330
331

        color_func : function or None, default=None
            Function to generate new color from word count, font size, position
            and orientation.  If None, self.color_func is used.

        Returns
        -------
        self
        """
332
        self._check_generated()
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365

        if color_func is None:
            color_func = self.color_func
        self.layout_ = [(word, font_size, position, orientation,
                         color_func(word, font_size, position, orientation, random_state))
                        for word, font_size, position, orientation, _ in self.layout_]
        return self

    def to_file(self, filename):
        """Export to image file.

        Parameters
        ----------
        filename : string
            Location to write to.

        Returns
        -------
        self
        """

        img = self.to_image()
        img.save(filename)
        return self

    def to_array(self):
        """Convert to numpy array.

        Returns
        -------
        image : nd-array size (width, height, 3)
            Word cloud image as numpy matrix.
        """
Andreas Mueller's avatar
Andreas Mueller committed
366
        return np.array(self.to_image())
367

Andreas Mueller's avatar
Andreas Mueller committed
368
    def __array__(self):
369
370
371
372
373
374
375
        """Convert to numpy array.

        Returns
        -------
        image : nd-array size (width, height, 3)
            Word cloud image as numpy matrix.
        """
Andreas Mueller's avatar
Andreas Mueller committed
376
        return self.to_array()
377
378
379

    def to_html(self):
        raise NotImplementedError("FIXME!!!")