MySQL データベースをテキスト分析に使用するにはどうすればよいですか?

CREATE DATABASE analysis;
USE analysis;
CREATE TABLE text_data (
    id INT PRIMARY KEY AUTO_INCREMENT,
    content TEXT
);

LOAD DATA INFILE 'path/to/text_data.csv'
INTO TABLE text_data
FIELDS TERMINATED BY ','
ENCLOSED BY '"'
LINES TERMINATED BY '
'
IGNORE 1 ROWS;

SELECT COUNT(*) FROM text_data;

SELECT SUM(LENGTH(content) - LENGTH(REPLACE(content, ' ', '')) + 1) FROM text_data;

SELECT * FROM text_data WHERE content LIKE '%keyword%';

SELECT word, COUNT(*) AS count FROM (
    SELECT DISTINCT SUBSTRING_INDEX(SUBSTRING_INDEX(content, ' ', n), ' ', -1) AS word
    FROM text_data
    JOIN (
        SELECT 1 AS n UNION ALL SELECT 2 UNION ALL SELECT 3 UNION ALL SELECT 4
    ) AS numbers
    ON CHAR_LENGTH(content) - CHAR_LENGTH(REPLACE(content, ' ', '')) >= n - 1
) AS words
GROUP BY word
ORDER BY count DESC
LIMIT 10;

SELECT CONCAT(word1, ' ', word2) AS phrase, COUNT(*) AS count FROM (
    SELECT DISTINCT
        SUBSTRING_INDEX(SUBSTRING_INDEX(content, ' ', n1), ' ', -1) AS word1,
        SUBSTRING_INDEX(SUBSTRING_INDEX(content, ' ', n2), ' ', -1) AS word2
    FROM text_data
    JOIN (
        SELECT a.n + b.n * 10 AS n1, a.n + b.n * 10 + 1 AS n2
        FROM (
            SELECT 1 AS n
            UNION ALL SELECT 2 UNION ALL SELECT 3 UNION ALL SELECT 4 UNION ALL SELECT 5
            UNION ALL SELECT 6 UNION ALL SELECT 7 UNION ALL SELECT 8 UNION ALL SELECT 9
        ) AS a
        CROSS JOIN (
            SELECT 0 AS n UNION ALL SELECT 1 UNION ALL SELECT 2 UNION ALL SELECT 3
        ) AS b
    ) AS numbers
    ON CHAR_LENGTH(content) - CHAR_LENGTH(REPLACE(content, ' ', '')) >= n2 - 1
) AS phrases
GROUP BY phrase
ORDER BY count DESC
LIMIT 10;

import matplotlib.pyplot as plt
import mysql.connector

cnx = mysql.connector.connect(user='your_username', password='your_password',
                              host='localhost',
                              database='analysis')
cursor = cnx.cursor()

query = ("SELECT word, COUNT(*) AS count FROM ("
         "SELECT DISTINCT SUBSTRING_INDEX(SUBSTRING_INDEX(content, ' ', n), ' ', -1) AS word "
         "FROM text_data "
         "JOIN ("
         "SELECT 1 AS n UNION ALL SELECT 2 UNION ALL SELECT 3 UNION ALL SELECT 4"
         ") AS numbers "
         "ON CHAR_LENGTH(content) - CHAR_LENGTH(REPLACE(content, ' ', '')) >= n - 1"
         ") AS words "
         "GROUP BY word "
         "ORDER BY count DESC "
         "LIMIT 10")

cursor.execute(query)

words = []
counts = []

for (word, count) in cursor:
    words.append(word)
    counts.append(count)

plt.bar(words, counts)
plt.xlabel('Word')
plt.ylabel('Count')
plt.title('Frequency of Top 10 Words')
plt.xticks(rotation=45)
plt.show()

cursor.close()
cnx.close()