From 0b73c877f36d43093c7b4fcd4cf662a40a58a95e Mon Sep 17 00:00:00 2001
From: tangwang <tangwang@essa.top>
Date: Thu, 23 Oct 2025 12:10:24 +0800
Subject: [PATCH] fix

---
 offline_tasks/a.py                         |  7 +++++++
 offline_tasks/scripts/a.py                 | 36 ------------------------------------
 offline_tasks/scripts/i2i_deepwalk.py      |  4 ++++
 offline_tasks/scripts/i2i_item_behavior.py |  4 ++++
 offline_tasks/scripts/i2i_session_w2v.py   |  4 ++++
 offline_tasks/scripts/i2i_swing.py         |  6 +++++-
 6 files changed, 24 insertions(+), 37 deletions(-)
 create mode 100644 offline_tasks/a.py
 delete mode 100644 offline_tasks/scripts/a.py

diff --git a/offline_tasks/a.py b/offline_tasks/a.py
new file mode 100644
index 0000000..caacc46
--- /dev/null
+++ b/offline_tasks/a.py
@@ -0,0 +1,7 @@
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.outputs import OutputKeys
+
+img_captioning = pipeline(Tasks.image_captioning, model='iic/ofa_image-caption_coco_distilled_en', model_revision='master')
+result = img_captioning('https://modelscope.oss-cn-beijing.aliyuncs.com/demo/image-captioning/donuts.jpeg')
+print(result[OutputKeys.CAPTION])  # 'a wooden table topped with different types of donuts'
\ No newline at end of file
diff --git a/offline_tasks/scripts/a.py b/offline_tasks/scripts/a.py
deleted file mode 100644
index b5e53fe..0000000
--- a/offline_tasks/scripts/a.py
+++ /dev/null
@@ -1,36 +0,0 @@
-from modelscope import AutoProcessor, Gemma3nForConditionalGeneration
-from PIL import Image
-import requests
-import torch
-model_id = "google/gemma-3n-e4b-it"
-model = Gemma3nForConditionalGeneration.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16,).eval()
-processor = AutoProcessor.from_pretrained(model_id)
-messages = [
-    {
-        "role": "system",
-        "content": [{"type": "text", "text": "You are a helpful assistant."}]
-    },
-    {
-        "role": "user",
-        "content": [
-            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
-            {"type": "text", "text": "Describe this image in detail."}
-        ]
-    }
-]
-inputs = processor.apply_chat_template(
-    messages,
-    add_generation_prompt=True,
-    tokenize=True,
-    return_dict=True,
-    return_tensors="pt",
-).to(model.device)
-input_len = inputs["input_ids"].shape[-1]
-with torch.inference_mode():
-    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
-    generation = generation[0][input_len:]
-decoded = processor.decode(generation, skip_special_tokens=True)
-print(decoded)
-# **Overall Impression:** The image is a close-up shot of a vibrant garden scene,
-# focusing on a cluster of pink cosmos flowers and a busy bumblebee.
-# It has a slightly soft, natural feel, likely captured in daylight.
\ No newline at end of file
diff --git a/offline_tasks/scripts/i2i_deepwalk.py b/offline_tasks/scripts/i2i_deepwalk.py
index 035cab8..973cdae 100644
--- a/offline_tasks/scripts/i2i_deepwalk.py
+++ b/offline_tasks/scripts/i2i_deepwalk.py
@@ -280,6 +280,10 @@ def main():
     df = pd.read_sql(sql_query, engine)
     logger.info(f"获取到 {len(df)} 条记录")
     
+    # 确保ID为整数类型
+    df['item_id'] = df['item_id'].astype(int)
+    df['user_id'] = df['user_id'].astype(str)
+    
     # 记录数据信息
     log_dataframe_info(logger, df, "用户行为数据")
     
diff --git a/offline_tasks/scripts/i2i_item_behavior.py b/offline_tasks/scripts/i2i_item_behavior.py
index 6920a69..07ae174 100644
--- a/offline_tasks/scripts/i2i_item_behavior.py
+++ b/offline_tasks/scripts/i2i_item_behavior.py
@@ -56,6 +56,10 @@ if args.debug:
 # 执行 SQL 查询并将结果加载到 pandas DataFrame
 df = pd.read_sql(sql_query, engine)
 
+# 确保ID为整数类型
+df['item_id'] = df['item_id'].astype(int)
+df['user_id'] = df['user_id'].astype(str)  # user_id保持为字符串
+
 if args.debug:
     print(f"[DEBUG] 查询完成，共 {len(df)} 条记录")
     print(f"[DEBUG] 唯一用户数: {df['user_id'].nunique()}")
diff --git a/offline_tasks/scripts/i2i_session_w2v.py b/offline_tasks/scripts/i2i_session_w2v.py
index ae9c634..a65be3a 100644
--- a/offline_tasks/scripts/i2i_session_w2v.py
+++ b/offline_tasks/scripts/i2i_session_w2v.py
@@ -227,6 +227,10 @@ def main():
     df = pd.read_sql(sql_query, engine)
     logger.info(f"获取到 {len(df)} 条记录")
     
+    # 确保ID为整数类型
+    df['item_id'] = df['item_id'].astype(int)
+    df['user_id'] = df['user_id'].astype(str)
+    
     # 记录数据信息
     log_dataframe_info(logger, df, "用户行为数据")
     
diff --git a/offline_tasks/scripts/i2i_swing.py b/offline_tasks/scripts/i2i_swing.py
index b6e7cb8..d2dc1d7 100644
--- a/offline_tasks/scripts/i2i_swing.py
+++ b/offline_tasks/scripts/i2i_swing.py
@@ -18,7 +18,7 @@ from config.offline_config import (
 from scripts.debug_utils import (
     setup_debug_logger, log_dataframe_info, log_dict_stats,
     save_readable_index, load_name_mappings_from_file, log_algorithm_params,
-    log_processing_step, clean_item_name
+    log_processing_step
 )
 
 
@@ -285,6 +285,10 @@ def main():
         df = pd.read_sql(sql_query, engine)
         logger.info(f"获取到 {len(df)} 条记录")
         
+        # 确保ID为整数类型
+        df['item_id'] = df['item_id'].astype(int)
+        df['user_id'] = df['user_id'].astype(str)
+        
         # Debug: 显示数据详情
         if args.debug:
             log_dataframe_info(logger, df, "用户行为数据", sample_size=10)
--
libgit2 0.21.2