Views
No views yet
remove_column_collisions() after joins.NaT and Nan with Python None.import statements are inside functions..to_dict('records').system, query, and response entries1from transformers import AutoModelForCausalLM, AutoTokenizer
2import torch
3
4# Load the model
5model = AutoModelForCausalLM.from_pretrained("10Prem09/finetuned_Qwen2.5_Coder_0.5B_Instruct", torch_dtype=torch.float16).cuda()
6tokenizer = AutoTokenizer.from_pretrained("10Prem09/finetuned_Qwen2.5_Coder_0.5B_Instruct")
7model.eval()
8
9# Define prompt using raw role tags (no chat template)
10system_prompt = "Role: Python Code Generator."
11user_prompt = "Merge employee and department data, then filter by department to calculate the average salary for each employee."
12prompt = f"<|system|>\n{system_prompt}\n<|user|>\n{user_prompt}\n<|assistant|>\n"
13
14# Tokenize input
15inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
16
17# Generate response
18with torch.no_grad():
19 outputs = model.generate(
20 **inputs,
21 max_new_tokens=300, # Ideally can be varied between 300 and 512.
22 repetition_penalty=1.3, # Can be changed from 1.2 to 1.4 to get ideal results.
23 pad_token_id=tokenizer.eos_token_id
24 )
25
26# Decode and print result
27generated_code = tokenizer.decode(outputs[0], skip_special_tokens=True)
28print(generated_code)
291
2{
3 "system": "Role: Python Code Generator...",
4 "query": "Analyze marketing campaign ROI by fiscal quarters, handling column collisions with a left join.",
5 "response": "```python\ndef campaign_roi_by_quarter(campaign_df, spending_df, fiscal_config):\n import pandas as pd\n import numpy as np\n campaign_df['launch_date'] = pd.to_datetime(campaign_df['launch_date'])\n campaign_df['year'] = campaign_df['launch_date'].dt.year\n campaign_df['month'] = campaign_df['launch_date'].dt.month\n\n def assign_quarter(row):\n for q, (start, end) in fiscal_config.items():\n m = row['month']\n if start > end:\n if m >= start or m <= end:\n return f\"Q{q} {row['year'] if m >= start else row['year']-1}\"\n elif start <= m <= end:\n return f\"Q{q} {row['year']}\"\n\n campaign_df['quarter'] = campaign_df.apply(assign_quarter, axis=1)\n merged_df = pd.merge(campaign_df, spending_df, on='campaign_id', how='left', suffixes=('', '_y'))\n merged_df = remove_column_collisions(merged_df, 'left')\n merged_df['roi'] = merged_df['revenue_generated'] / merged_df['spending']\n result = merged_df.groupby('quarter')['roi'].mean().reset_index()\n result.replace({pd.NaT: None, np.nan: None}, inplace=True)\n return result.to_dict('records')\n\nfiscal_config = {1: (7,9), 2: (10,12), 3: (1,3), 4: (4,6)}\nresult = campaign_roi_by_quarter(source1, source2, fiscal_config)\n```"
6}1{
2 "system": "Role: Python Code Generator...",
3 "query": "Track supplier deliveries by fiscal quarters: Q1 (March-May), Q2 (June-August), Q3 (September-November), Q4 (December-February).",
4 "response": "```python\ndef deliveries_by_quarter(deliveries_df, fiscal_config):\n import pandas as pd\n import numpy as np\n deliveries_df['delivery_date'] = pd.to_datetime(deliveries_df['delivery_date'])\n deliveries_df['year'] = deliveries_df['delivery_date'].dt.year\n deliveries_df['month'] = deliveries_df['delivery_date'].dt.month\n\n def assign_quarter(row):\n for q, (start, end) in fiscal_config.items():\n m = row['month']\n if start > end:\n if m >= start or m <= end:\n return f\"Q{q} {row['year'] if m >= start else row['year']-1}\"\n elif start <= m <= end:\n return f\"Q{q} {row['year']}\"\n\n deliveries_df['quarter'] = deliveries_df.apply(assign_quarter, axis=1)\n result = deliveries_df.groupby('quarter').size().reset_index(name='delivery_count')\n result.replace({pd.NaT: None, np.nan: None}, inplace=True)\n return result.to_dict('records')\n\nfiscal_config = {1: (3, 5), 2: (6, 8), 3: (9, 11), 4: (12, 2)}\nresult = deliveries_by_quarter(source1, fiscal_config)\n```"
5}1{
2 "system": "Role: Python Code Generator. Generate clean, function-based Python code based on user requests.",
3 "query": "Find all projects and their associated manager names by joining project and employee data.",
4 "response": "```python\ndef get_project_manager_info(projects_df, employees_df):\n import pandas as pd\n import numpy as np\n\n merged = projects_df.merge(employees_df, left_on='manager_id', right_on='employee_id', how='left')\n merged = remove_column_collisions(merged, 'left')\n\n result = merged[['project_name', 'manager_name']]\n result.replace({pd.NaT: None, np.nan: None}, inplace=True)\n\n return result.to_dict('records')\n\nresult = get_project_manager_info(source1, source2)\n```"
5}