使用 Python 查找关键字类别的搜索量上限¶

import pandas as pd
%load_ext google.colab.data_table

df = pd.read_csv("rckey.csv")['Keyword']
df2 = pd.read_csv("rckey.csv")

df = df.str.split().explode().value_counts().reset_index()

stop = ['1','2','3','4','5','6','7','8','9','get','ourselves', 'hers','us','there','you','for','that','as','between', 'yourself', 'but', 'again', 'there', 'about', 'once', 'during', 'out', 'very', 'having', 'with', 'they', 'own', 'an', 'be', 'some', 'for', 'do', 'its', 'yours', 'such', 'into', 'of', 'most', 'itself', 'other', 'off', 'is', 's', 'am', 'or', 'who', 'as', 'from', 'him', 'each', 'the', 'themselves', 'until', 'below', 'are', 'we', 'these', 'your', 'his', 'through', 'don', 'nor', 'me', 'were', 'her', 'more', 'himself', 'this', 'down', 'should', 'our', 'their', 'while', 'above', 'both', 'up', 'to', 'ours', 'had', 'she', 'all', 'no', 'when', 'at', 'any', 'before', 'them', 'same', 'and', 'been', 'have', 'in', 'will', 'on', 'does', 'yourselves', 'then', 'that', 'because', 'what', 'over', 'why', 'so', 'can', 'did', 'not', 'now', 'under', 'he', 'you', 'herself', 'has', 'just', 'where', 'too', 'only', 'myself', 'which', 'those', 'i', 'after', 'few', 'whom', 't', 'being', 'if', 'theirs', 'my', 'against', 'a', 'by', 'doing', 'it', 'how', 'further', 'was', 'here', 'than']

df = df[~df['index'].isin(stop)].reset_index()

topkeywords = df['index'][:20].to_list()
print(topkeywords)

df[:20].plot.bar(y='Keyword', x='index', figsize=(15,5), title="Volume", rot=20)

regex = '(' + ('|'.join(topkeywords)) + ')'
df2['Marked'] = df2.Keyword.str.extract(regex)
df2 = df2.dropna()

df2 = df2.groupby(['Marked'])['Search Volume'].sum().to_frame().sort_values('Search Volume', ascending=False).reset_index()
df2.head()

df2.plot.bar(y='Search Volume', x='Marked', figsize=(15,5), title="Keyword Search Volume Ceiling", xlabel="Tag", ylabel="Search Volume", rot=20)