在Python中自然语言处理生成词云WordCloud

git clone https://github.com/amueller/word_cloud.gitcd word_cloudpip install .

# Start with loading all necessary librariesimport numpy as npimport pandas as pdfrom os import pathfrom PIL import Imagefrom wordcloud import WordCloud, STOPWORDS, ImageColorGeneratorimport matplotlib.pyplot as plt% matplotlib inline

c:\intelpython3\lib\site-packages\matplotlib\__init__.py:import warningswarnings.filterwarnings("ignore")

# Load in the dataframedf = pd.read_csv("data/winemag-data-130k-v2.csv", index_col=0)

# Looking at first 5 rows of the datasetdf.head()

print("There are {} observations and {} features in this dataset. \n".format(df.shape[0],df.shape[1]))print("There are {} types of wine in this dataset such as {}... \n".format(len(df.variety.unique()),                                                                           ", ".join(df.variety.unique()[0:5])))print("There are {} countries producing wine in this dataset such as {}... \n".format(len(df.country.unique()),                                                                                      ", ".join(df.country.unique()[0:5])))

There are 129971 observations and 13 features in this dataset.There are 708 types of wine in this dataset such as White Blend, Portuguese Red, Pinot Gris, Riesling, Pinot Noir...There are 44 countries producing wine in this dataset such as Italy, Portugal, US, Spain, France...

df[["country", "description","points"]].head()

plt.ylabel("Number of Wines")plt.show()

plt.ylabel("Highest point of Wines")plt.show()

?WordCloud

/*
* 提示：该行代码过长，系统自动注释不进行高亮。一键复制会移除系统注释 
* [1;31mInit signature:[0m [0mWordCloud[0m[1;33m([0m[0mfont_path[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mwidth[0m[1;33m=[0m[1;36m400[0m[1;33m,[0m [0mheight[0m[1;33m=[0m[1;36m200[0m[1;33m,[0m [0mmargin[0m[1;33m=[0m[1;36m2[0m[1;33m,[0m [0mranks_only[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mprefer_horizontal[0m[1;33m=[0m[1;36m0.9[0m[1;33m,[0m [0mmask[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mscale[0m[1;33m=[0m[1;36m1[0m[1;33m,[0m [0mcolor_func[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mmax_words[0m[1;33m=[0m[1;36m200[0m[1;33m,[0m [0mmin_font_size[0m[1;33m=[0m[1;36m4[0m[1;33m,[0m [0mstopwords[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mrandom_state[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mbackground_color[0m[1;33m=[0m[1;34m'black'[0m[1;33m,[0m [0mmax_font_size[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mfont_step[0m[1;33m=[0m[1;36m1[0m[1;33m,[0m [0mmode[0m[1;33m=[0m[1;34m'RGB'[0m[1;33m,[0m [0mrelative_scaling[0m[1;33m=[0m[1;36m0.5[0m[1;33m,[0m [0mregexp[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mcollocations[0m[1;33m=[0m[1;32mTrue[0m[1;33m,[0m [0mcolormap[0m[1;33m=[0m[1;32mNone[0m[1;33m,[0m [0mnormalize_plurals[0m[1;33m=[0m[1;32mTrue[0m[1;33m,[0m [0mcontour_width[0m[1;33m=[0m[1;36m0[0m[1;33m,[0m [0mcontour_color[0m[1;33m=[0m[1;34m'black'[0m[1;33m)[0m[1;33m[0m[0m[1;31mDocstring:[0m     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 on a Linux machine. If you are on    another OS or don't have this font; you need to adjust this path.width : int (default=400)    Width of the canvas.height : int (default=200)    Height of the canvas.prefer_horizontal : float (default=0.90)    The ratio of times to try horizontal fitting as opposed to vertical.    If prefer_horizontal < 1, the algorithm will try rotating the word    if it doesn't fit. (There is currently no built-in way to get only    vertical words.)mask : nd-array or None (default=None)    If not None, gives a binary mask on where to draw words. If mask is not    None, width and height will be ignored, and the shape of mask will be    used instead. All white (#FF or #FFFFFF) entries will be considered    "masked out" while other entries will be free to draw on. [This    changed in the most recent version!]contour_width: float (default=0)    If mask is not None and contour_width > 0, draw the mask contour.contour_color: color value (default="black")    Mask contour color.scale : float (default=1)    Scaling between computation and drawing. For large word-cloud images,    using scale instead of larger canvas size is significantly faster, but    might lead to a coarser fit for the words.min_font_size : int (default=4)    Smallest font size to use. Will stop when there is no more room in this    size.font_step : int (default=1)    Step size for the font. font_step > 1 might speed up computation but    give a worse fit.max_words : number (default=200)    The maximum number of words.stopwords : set of strings or None    The words that will be eliminated. If None, the build-in STOPWORDS    list will be used.background_color : color value (default="black")    Background color for the word cloud image.max_font_size : int or None (default=None)    Maximum font size for the largest word. If None, the height of the image is    used.mode : string (default="RGB")    Transparent background will be generated when mode is "RGBA" and    background_color is None.relative_scaling : float (default=.5)    Importance of relative word frequencies for font-size.  With    relative_scaling=0, only word-ranks are considered.  With    relative_scaling=1, a word that is twice as frequent will have twice    the size.  If you want to consider the word frequencies and not only    their rank, relative_scaling around .5 often looks good.    .. versionchanged: 2.0        Default is now 0.5.color_func : callable, default=None    Callable with parameters word, font_size, position, orientation,    font_path, random_state that returns a PIL color for each word.    Overwrites "colormap".    See colormap for specifying a matplotlib colormap instead.regexp : string or None (optional)    Regular expression to split the input text into tokens in process_text.    If None is specified, ``r"\w[\w']+"`` is used.collocations : bool, default=True    Whether to include collocations (bigrams) of two words.    .. versionadded: 2.0colormap : string or matplotlib colormap, default="viridis"    Matplotlib colormap to randomly draw colors from for each word.    Ignored if "color_func" is specified.    .. versionadded: 2.0normalize_plurals : bool, default=True    Whether to remove trailing 's' from words. If True and a word    appears with and without a trailing 's', the one with trailing 's'    is removed and its counts are added to the version without    trailing 's' -- unless the word ends with 'ss'.Attributes----------``words_`` : dict of string to float    Word tokens with associated frequency.    .. versionchanged: 2.0        ``words_`` is now a dictionary``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 will make the code significantly slower. If you need alarge word cloud, try a lower canvas size, and set the scale parameter.The algorithm might give more weight to the ranking of the wordsthen their actual frequencies, depending on the ``max_font_size`` and thescaling heuristic.[1;31mFile:[0m           c:\intelpython3\lib\site-packages\wordcloud\wordcloud.py[1;31mType:[0m           type
*/

# Display the generated image:plt.imshow(wordcloud, interpolation='bilinear')plt.axis("off")plt.show()

plt.imshow(wordcloud, interpolation="bilinear")plt.axis("off")plt.show()

# Save the image in the img folder:wordcloud.to_file("img/first_review.png")

<wordcloud.wordcloud.WordCloud at 0x16f1d704978>

print ("There are {} words in the combination of all review.".format(len(text)))

There are 31661073 words in the combination of all review.

# Display the generated image:# the matplotlib way:plt.imshow(wordcloud, interpolation='bilinear')plt.axis("off")plt.show()

array([[0, 0, 0, ..., 0, 0, 0],       [0, 0, 0, ..., 0, 0, 0],       [0, 0, 0, ..., 0, 0, 0],       ...,       [0, 0, 0, ..., 0, 0, 0],       [0, 0, 0, ..., 0, 0, 0],       [0, 0, 0, ..., 0, 0, 0]], dtype=uint8)

def transform_format(val):    if val == 0:        return 255    else:        return val

现在，您将以正确的形式创建一个新的蒙版。

array([[255, 255, 255, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255],       ...,       [255, 255, 255, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255],       [255, 255, 255, ..., 255, 255, 255]])

# showplt.figure(figsize=[20,10])plt.imshow(wc, interpolation='bilinear')plt.axis("off")plt.show()

countryUS          54504France      22093Italy       19540Spain        6645Portugal     5691dtype: int64

countryUS           54504France       22093Italy        19540Spain         6645Portugal      5691Chile         4472Argentina     3800Austria       3345Australia     2329Germany       2165dtype: int64

# store to fileplt.savefig("img/us_wine.png", format="png")plt.show()

# store to fileplt.savefig("img/fra_wine.png", format="png")#plt.show()

# store to fileplt.savefig("img/ita_wine.png", format="png")#plt.show()

# store to fileplt.savefig("img/spa_wine.png", format="png")#plt.show()

# store to fileplt.savefig("img/por_wine.png", format="png")#plt.show()