Created
January 18, 2020 13:23
-
-
Save madawei2699/03b777db40b5461b05d94bc99e29f878 to your computer and use it in GitHub Desktop.
TF-IDF计算网页相似度
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import gensim | |
from gensim import corpora,models | |
from gensim.matutils import corpus2dense | |
from sklearn.metrics.pairwise import cosine_similarity | |
import pandas as pd | |
import numpy as np | |
import seaborn as sns | |
import matplotlib.pyplot as plt | |
import os | |
import datetime | |
import random | |
root_dir = './mySpider/' | |
def get_documents(names): | |
documents = [] | |
for f in names: | |
with open(root_dir + 'text/' + f + '.html.txt', 'r') as f: | |
documents.append(f.read()) | |
return [[word for word in document.lower().split()] for document in documents] | |
def get_urls(): | |
url_list = [] | |
with open(root_dir + 'urls.txt', 'r') as f: | |
url_list.extend(f.readlines()) | |
return [u.replace('\n', '').split('/')[-2] for u in url_list] | |
def calc_tfidf(texts): | |
dictionary = corpora.Dictionary(texts) | |
corpus = [dictionary.doc2bow(text) for text in texts] | |
tfidf_model = models.TfidfModel(corpus) | |
corpus_tfidf = tfidf_model[corpus] | |
corpus_matrix=corpus2dense(corpus_tfidf, len(dictionary)) | |
return np.asmatrix(corpus_matrix.T) | |
def get_index(value): | |
index_label = [float("%0.2f"%i) for i in np.linspace(0.1,1,10)] | |
for idx, val in enumerate(index_label): | |
if value <= val: | |
return idx | |
return -1 | |
def calc_cosine_similarity(tfidf, colums): | |
rows = [] | |
index_label = [float("%0.2f"%i) for i in np.linspace(0.1,1,10)] | |
count_list = [0] * 10 | |
tfidf_list = [] | |
for x in range(len(tfidf)): | |
cols = [] | |
for y in range(len(tfidf)): | |
if y > x: | |
sim = cosine_similarity(tfidf[x], tfidf[y]) | |
cols.append(sim[0][0]) | |
idx = get_index(sim[0][0]) | |
if idx != -1: | |
count_list[idx] += 1 | |
tfidf_list.append(sim[0][0]) | |
elif y == x: | |
cols.append(1) | |
else: | |
cols.append(rows[y][x]) | |
rows.append(cols) | |
print("time: [" + str(datetime.datetime.now()) + "], x: " + str(x) + ", sim: " + str(rows[x])) | |
return pd.DataFrame(data=rows, index=colums, columns=colums), count_list, index_label, tfidf_list | |
def draw_heatmap(df): | |
# Generate a mask for the upper triangle | |
mask = np.zeros_like(df, dtype=np.bool) | |
mask[np.triu_indices_from(mask)] = True | |
# Set up the matplotlib figure | |
f, ax = plt.subplots(figsize=(30, 30)) | |
# Generate a custom diverging colormap | |
cmap = sns.diverging_palette(220, 10, as_cmap=True) | |
# Draw the heatmap with the mask and correct aspect ratio | |
sns.heatmap(df, mask=mask, cmap=cmap, vmax=1, center=0, | |
square=True, linewidths=.1, cbar_kws={"shrink": .05}) | |
plt.savefig(root_dir + 'hasoffer_heatmap.png') | |
def draw_barplot(data, columns): | |
fig, ax = plt.subplots() | |
df = pd.DataFrame({"counts": data, "sim": columns}) | |
sns.set(style="whitegrid") | |
ax = sns.barplot(x="sim", y="counts", data=df) | |
plt.savefig(root_dir + 'hasoffer_barplot.png') | |
def draw_histogram(data): | |
fig, ax = plt.subplots() | |
sns.set(color_codes=True) | |
sns.kdeplot(data, shade=True, cut=0) | |
sns.rugplot(data) | |
plt.savefig(root_dir + 'hasoffer_histogram.png') | |
names = random.sample(get_urls(), 1300) | |
df, counts, hist_columns, tfidf_list = calc_cosine_similarity(calc_tfidf(get_documents(names)), names) | |
df.to_csv(root_dir + 'hasoffer_page_simular.csv') | |
draw_heatmap(df) | |
draw_barplot(counts, hist_columns) | |
draw_histogram(tfidf_list) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment