File size: 5,989 Bytes
b284540
 
 
 
 
 
 
0df5c07
 
 
 
 
 
 
 
 
b284540
 
 
 
 
0df5c07
b284540
 
 
 
 
 
 
 
0df5c07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b284540
 
 
 
 
 
0df5c07
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b284540
 
0df5c07
b284540
 
 
 
 
 
 
 
 
 
 
0df5c07
 
b284540
 
 
 
 
0df5c07
b284540
0df5c07
 
b284540
 
 
 
0df5c07
b284540
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
# process_hf_dataset.py
from datasets import load_dataset
import re
from parser import parse_python_code
from database import init_chromadb, store_program, DB_NAME, HF_DATASET_NAME, HF_KEY
import chromadb

def rename_variables(code, variable_prefixes=None):
    """Rename variables in Python code to align with vector categories (input_variable, assigned_variable, returned_variable)."""
    if variable_prefixes is None:
        variable_prefixes = {
            'input': 'input_variable',
            'assigned': 'assigned_variable',
            'returned': 'returned_variable'
        }
    
    # Simple variable name detection and renaming
    pattern = r'\b[a-zA-Z_]\w*\b'  # Match variable names (simple heuristic)
    variables = set()
    code_lines = code.split('\n')
    
    # Find all variable names (simplified approach, could improve with AST)
    for line in code_lines:
        matches = re.findall(pattern, line)
        for match in matches:
            if match not in ['def', 'if', 'else', 'for', 'while', 'return', 'import', 'print', 'eval', 'str', 'int']:  # Exclude keywords
                variables.add(match)
    
    # Sort variables by first appearance (simplified, could improve with AST)
    sorted_vars = sorted(list(variables))
    var_map = {}
    var_count = {prefix: 1 for prefix in variable_prefixes.values()}
    
    # Assign variables based on context (simplified heuristic)
    for var in sorted_vars:
        # Determine variable role based on context (simplified)
        if var in ['expression', 'input']:  # Assume input parameters or initial variables
            role = 'input_variable'
        elif var in code.split() and 'return' in line for line in code_lines if var in line:  # Returned variables
            role = 'returned_variable'
        else:  # Default to assigned variables
            role = 'assigned_variable'
        
        new_name = f"{role}{var_count[role]}"
        var_map[var] = new_name
        var_count[role] += 1
    
    # Replace variables in code
    new_code = code
    for old_var, new_var in var_map.items():
        new_code = re.sub(r'\b' + old_var + r'\b', new_var, new_code)
    
    return new_code, var_map

def generate_description_tokens(sequence, vectors, var_map=None):
    """Generate semantic description tokens for a program, including variable roles."""
    tokens = []
    category_descriptions = {
        'import': 'imports module',
        'function': 'defines function',
        'assigned_variable': 'assigns variable',
        'input_variable': 'input parameter',
        'returned_variable': 'returns value',
        'if': 'conditional statement',
        'return': 'returns result',
        'try': 'try block',
        'except': 'exception handler',
        'expression': 'expression statement',
        'spacer': 'empty line or comment'
    }
    
    for cat, vec in zip(sequence, vectors):
        if cat in category_descriptions:
            tokens.append(f"{category_descriptions[cat]}:{cat}")
            # Add vector-derived features (e.g., level, span) as tokens
            tokens.append(f"level:{vec[1]}")
            tokens.append(f"span:{vec[3]:.2f}")
    
    # Add variable role tokens if var_map exists
    if var_map:
        for old_var, new_var in var_map.items():
            role = new_var.split('variable')[0] + 'variable'  # Extract role (e.g., 'input_variable')
            tokens.append(f"variable:{old_var}={new_var}:{role}")
    
    return tokens

def process_hf_dataset():
    """Process the Hugging Face dataset and store programs in ChromaDB, aligning with vector categories."""
    # Load the dataset
    dataset = load_dataset("iamtarun/python_code_instructions_18k_alpaca", split="train")
    
    # Initialize ChromaDB client
    client = init_chromadb()
    
    # Process each entry
    for entry in dataset:
        instruction = entry['instruction']
        output = entry['output']
        
        # Rename variables to align with vector categories
        processed_code, var_map = rename_variables(output)
        
        # Parse the code to get parts and sequence
        parts, sequence = parse_python_code(processed_code)
        vectors = [part['vector'] for part in parts]
        
        # Generate description tokens including variable roles
        description_tokens = f"task:{instruction.replace(' ', '_')}"
        description_tokens_list = generate_description_tokens(sequence, vectors, var_map)
        description_tokens += " " + " ".join(description_tokens_list)
        
        # Store in ChromaDB with description
        store_program(client, processed_code, sequence, vectors, DB_NAME)
        
        # Update metadata with instruction and variable roles as description
        collection = client.get_collection(DB_NAME)
        program_id = str(hash(processed_code))
        collection.update(
            ids=[program_id],
            metadatas=[{"sequence": ",".join(sequence), "description_tokens": description_tokens}]
        )
    
    # Save to Hugging Face Dataset
    save_chromadb_to_hf()

def save_chromadb_to_hf(dataset_name=HF_DATASET_NAME, token=HF_KEY):
    """Save ChromaDB data to Hugging Face Dataset."""
    client = init_chromadb()
    collection = client.get_collection(DB_NAME)
    
    # Fetch all data from ChromaDB
    results = collection.get(include=["documents", "metadatas", "embeddings"])
    data = {
        "code": results["documents"],
        "sequence": [meta["sequence"] for meta in results["metadatas"]],
        "vectors": results["embeddings"],  # ChromaDB already flattens embeddings
        "description_tokens": [meta.get('description_tokens', '') for meta in results["metadatas"]]
    }
    
    # Create a Hugging Face Dataset
    dataset = Dataset.from_dict(data)
    
    # Push to Hugging Face Hub
    dataset.push_to_hub(dataset_name, token=token)
    print(f"Dataset pushed to Hugging Face Hub as {dataset_name}")

if __name__ == "__main__":
    process_hf_dataset()