没有那么多人喜欢你

import pandas as pd import sqlite3 def feature_deal(input_db, output_db): # 连接输入数据库 conn = sqlite3.connect(input_db) cursor = conn.cursor() # 从数据库中查询数据并转换为 DataFrame query = "SELECT * FROM your_table_name" # 替换为你的表名 cursor.execute(query) data = cursor.fetchall() columns = [description[0] for description in cursor.description] df = pd.DataFrame(data, columns=columns) # 数据处理代码... df = data.dropna(axis=1, how='all') label_feature = ['defectName-1', 'defectName-2'] null_precentile = df.isnull().sum() / len(df) dropcol_list1 = null_precentile[null_precentile.values > 0.97].index.tolist() df.drop(columns=dropcol_list1, inplace=True) text_columns = [col for col in df.columns if df[col].apply(lambda x: isinstance(x, str) and len(x) >= 50).any()] categorical_columns = df.select_dtypes(include=['object']).columns.to_list() dropcol_list2 = label_feature + text_columns categorical_columns = [cat for cat in categorical_columns if cat not in dropcol_list2] for col in categorical_columns: df[col] = df[col].str.strip() df[col] = df[col].astype('str') # 导入到新的数据库 new_conn = sqlite3.connect(output_db) df.to_sql('new_table_name', new_conn, if_exists='replace', index=False) # 替换为你的新表名 # 关闭数据库连接 conn.close() new_conn.close() # 调用函数 input_db = 'input.sqlite' output_db = 'output.sqlite' feature_deal(input_db, output_db)