Create 期刊论文投稿推荐系统.py

期刊论文投稿推荐系统.py

@@ -0,0 +1,141 @@
+from transformers import PegasusForConditionalGeneration
+from tokenizers_pegasus import PegasusTokenizer
+import re
+import pandas as pd
+import jieba
+import jieba.analyse as jay
+import paddle
+from pyecharts import options as opts
+from pyecharts.charts import Funnel
+
+
+paddle.enable_static()
+# -*- coding: utf-8 -*-
+
+ARTICLE_PATH = '2.xlsx'
+CACHE_PATH = ''
+def get_keywords_in_article():
+    def key_word(data):
+        data = str(data).strip()
+        result = re.findall(pattern='pan>(.*?)</t', string=data, flags=re.S)
+        str_n = []
+        for str_ in result:
+            str_ = re.sub(r'[0-9a-zA-Z“”]', '', str_)
+            if str_ == '':
+                continue
+            str_n.append(str_)
+        return str_n
+
+    excel_pd = pd.read_excel(ARTICLE_PATH, index_col=None, sheet_name=0)
+    # keyword_excel_pd = excel_pd['字段1'].values.tolist()
+    keyword_excel_list = []
+    for fil in excel_pd['字段1'].values.tolist():
+        keyword_excel_list.append(key_word(fil))
+    keyword_excel_pd = pd.DataFrame(keyword_excel_list)
+
+    excel_pd['字段1'] = excel_pd['字段1'].map(key_word)
+    excel_pd.columns = ['期刊名称', '2022复合影响因子', '2022综合影响因子', '关键词']
+
+    keyword_excel_new_pd = pd.concat([excel_pd, keyword_excel_pd.iloc[:, :20]], axis=1)
+    columns_list = [
+        '期刊名称',
+        '2022复合影响因子',
+        '2022综合影响因子',
+        '关键词',
+        '关键词1',
+        '关键词2',
+        '关键词3',
+        '关键词4',
+        '关键词5',
+        '关键词6',
+        '关键词7',
+        '关键词8',
+        '关键词9',
+        '关键词10',
+        '关键词11',
+        '关键词12',
+        '关键词13',
+        '关键词14',
+        '关键词15',
+        '关键词16',
+        '关键词17',
+        '关键词18',
+        '关键词19',
+        '关键词20',
+    ]
+    keyword_excel_new_pd.columns = columns_list
+    keyword_excel_new_pd.to_excel('3.xlsx')
+    excel_pd_1 = excel_pd.iloc[:, 3:].values.tolist()
+    new_list = [tokens for st in excel_pd_1 for tokens in st]
+    new_list = [tokens for st in new_list for tokens in st]
+    new_list = list(set(new_list))
+    return new_list, keyword_excel_new_pd
+
+def extract_tags(text):
+
+    new_list, keyword_excel_new_pd = get_keywords_in_article()
+    model = PegasusForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Pegasus-238M-Summary-Chinese")
+    tokenizer = PegasusTokenizer.from_pretrained("IDEA-CCNL/Randeng-Pegasus-238M-Summary-Chinese")
+
+
+    inputs = tokenizer(text, max_length=1024, return_tensors="pt")
+
+
+    summary_ids = model.generate(inputs["input_ids"])
+    data_decode = tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+
+
+
+
+    print(data_decode)
+    for i in range(len(new_list)):
+        jieba.add_word(new_list[i])
+    cut_result_str = jieba.cut(data_decode, use_paddle=True)
+    print("Paddle Mode: " + '/'.join(cut_result_str))
+    tok_result = jay.extract_tags(data_decode, topK=1, withWeight=False)
+    # print(tok_result[0])
+    # key_word_search_result = keyword_excel_new_pd.loc[keyword_excel_new_pd['关键词2'].isin(['数字经济'])]
+    # print(key_word_search_result)
+
+    # empty_pd = pd.DataFrame()
+    cache_path = '4.csv'
+    # empty_list = []
+    for i in range(1, 21):
+        key_word_search_result = keyword_excel_new_pd.loc[keyword_excel_new_pd[f'关键词{i}'].isin([str(tok_result[0])])]
+        key_word_search_result.to_csv(cache_path, mode='a+', columns=None)
+    pro_pd = pd.read_csv(cache_path)
+
+    pro_pd = pro_pd.dropna()
+    pro_new_pd = pro_pd.iloc[:, 1:]
+    pro_new_pd = pro_new_pd.drop_duplicates('2022综合影响因子')
+    pro_new_pd['2022复合影响因子'] = pro_new_pd['2022复合影响因子'].str[13:].astype('float64')
+    pro_new_pd.sort_values(by=['2022复合影响因子'], ascending=False, inplace=True)
+
+    pro_new_pd.to_excel('4.xlsx')
+    labels = []
+    values_1 = []
+    values_2 = []
+    for index, row in pro_new_pd.iterrows():
+        labels.append(row['期刊名称'])
+        values_1.append(row['2022复合影响因子'])
+        values_2.append(row['2022综合影响因子'].split('：')[1])
+    # figure_get(labels, values_1)
+
+    return [labels, values_1]
+
+def figure_get(labels, values_1):
+
+    c = (
+        Funnel(
+        )
+        .add(
+            '根据您的论文所推荐期刊',
+            [list(z) for z in zip(labels[:10], values_1[:10])],
+            label_opts=opts.LabelOpts(position="inside", is_show=True),
+        )
+        .set_global_opts(title_opts=opts.TitleOpts(title="根据您的论文所推荐的期刊"),
+                         legend_opts=opts.LegendOpts(is_show=False),
+                         toolbox_opts=opts.ToolboxOpts(is_show=False),
+                         )
+        .render("根据您的论文所推荐的期刊.html")
+    )