75 lines
2.2 KiB
Python
75 lines
2.2 KiB
Python
import pandas as pd
|
|
import psycopg2
|
|
from psycopg2.extras import RealDictCursor
|
|
|
|
# 数据库连接配置
|
|
conn = psycopg2.connect(
|
|
host="bj-postgres-16pob4sg.sql.tencentcdb.com",
|
|
port=28591,
|
|
user="ai_member",
|
|
password="LdfjdjL83h3h3^$&**YGG*",
|
|
dbname="vala_bi"
|
|
)
|
|
|
|
user_ids = [51, 17690, 17646, 2705]
|
|
|
|
# 1. 查询用户注册信息
|
|
query_register = """
|
|
SELECT id as user_id, created_at as register_time, status as user_status, tel as user_mobile
|
|
FROM bi_vala_app_account
|
|
WHERE id IN %s
|
|
"""
|
|
df_register = pd.read_sql(query_register, conn, params=(tuple(user_ids),))
|
|
|
|
# 2. 查询用户购课情况
|
|
query_purchase = """
|
|
SELECT account_id as user_id,
|
|
COUNT(*) as purchased_course_count,
|
|
SUM(pay_amount_int)/100.0 as total_paid_amount,
|
|
MAX(created_at) as last_purchase_time
|
|
FROM bi_vala_order
|
|
WHERE account_id IN %s AND pay_amount_int > 0
|
|
GROUP BY account_id
|
|
"""
|
|
df_purchase = pd.read_sql(query_purchase, conn, params=(tuple(user_ids),))
|
|
|
|
# 3. 查询用户学习进度
|
|
query_learn = """
|
|
SELECT account_id as user_id,
|
|
course_level,
|
|
latest_unit_index as current_unit,
|
|
latest_lesson_index as current_lesson,
|
|
learn_duration as total_learn_seconds,
|
|
last_learn_time
|
|
FROM bi_user_course_detail
|
|
WHERE account_id IN %s
|
|
"""
|
|
df_learn = pd.read_sql(query_learn, conn, params=(tuple(user_ids),))
|
|
|
|
# 合并数据
|
|
df_result = df_register.merge(df_purchase, on='user_id', how='left')
|
|
df_result = df_result.merge(df_learn, on='user_id', how='left')
|
|
|
|
# 填充空值
|
|
df_result = df_result.fillna({
|
|
'purchased_course_count': 0,
|
|
'total_paid_amount': 0,
|
|
'learning_course_count': 0,
|
|
'average_progress_percent': 0
|
|
})
|
|
|
|
# 格式化时间列
|
|
df_result['register_time'] = df_result['register_time'].dt.strftime('%Y-%m-%d %H:%M:%S')
|
|
df_result['last_purchase_time'] = pd.to_datetime(df_result['last_purchase_time']).dt.strftime('%Y-%m-%d %H:%M:%S')
|
|
df_result['last_learn_time'] = pd.to_datetime(df_result['last_learn_time']).dt.strftime('%Y-%m-%d %H:%M:%S')
|
|
|
|
# 导出为Excel
|
|
output_path = '/root/.openclaw/workspace/用户详细信息.xlsx'
|
|
df_result.to_excel(output_path, index=False, sheet_name='用户信息')
|
|
|
|
print(f"文件已生成：{output_path}")
|
|
print("数据预览：")
|
|
print(df_result.to_csv(sep='\t', na_rep='无'))
|
|
|
|
conn.close()
|