unixcoder

Model Description

UniXcoder is a unified cross-modal pre-trained model that leverages multimodal data (i.e. code comment and AST) to pretrain code representation.

• Developed by: Microsoft Team
• Shared by [Optional]: Hugging Face
• Model type: Feature Engineering
• Language(s) (NLP): en
• License: Apache-2.0
• Related Models:
  • Parent Model: RoBERTa
• Resources for more information:
  • Associated Paper

Uses

1. Dependency

• pip install torch
• pip install transformers

2. Quick Tour

We implement a class to use UniXcoder and you can follow the code to build UniXcoder. You can download the class by

wget https://raw.githubusercontent.com/microsoft/CodeBERT/master/UniXcoder/unixcoder.py

import torch
from unixcoder import UniXcoder

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = UniXcoder("microsoft/unixcoder-base")
model.to(device)

In the following, we will give zero-shot examples for several tasks under different mode, including code search (encoder-only), code completion (decoder-only), function name prediction (encoder-decoder) , API recommendation (encoder-decoder), code summarization (encoder-decoder).

3. Encoder-only Mode

For encoder-only mode, we give an example of code search.

1) Code and NL Embeddings

Here, we give an example to obtain code fragment embedding from CodeBERT.

# Encode maximum function
func = "def f(a,b): if a>b: return a else return b"
tokens_ids = model.tokenize([func],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
tokens_embeddings,max_func_embedding = model(source_ids)

# Encode minimum function
func = "def f(a,b): if a<b: return a else return b"
tokens_ids = model.tokenize([func],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
tokens_embeddings,min_func_embedding = model(source_ids)

# Encode NL
nl = "return maximum value"
tokens_ids = model.tokenize([nl],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
tokens_embeddings,nl_embedding = model(source_ids)

print(max_func_embedding.shape)
print(max_func_embedding)

torch.Size([1, 768])
tensor([[ 8.6533e-01, -1.9796e+00, -8.6849e-01,  4.2652e-01, -5.3696e-01,
         -1.5521e-01,  5.3770e-01,  3.4199e-01,  3.6305e-01, -3.9391e-01,
         -1.1816e+00,  2.6010e+00, -7.7133e-01,  1.8441e+00,  2.3645e+00,
				 ...,
         -2.9188e+00,  1.2555e+00, -1.9953e+00, -1.9795e+00,  1.7279e+00,
          6.4590e-01, -5.2769e-02,  2.4965e-01,  2.3962e-02,  5.9996e-02,
          2.5659e+00,  3.6533e+00,  2.0301e+00]], device='cuda:0',
       grad_fn=)

2) Similarity between code and NL

Now, we calculate cosine similarity between NL and two functions. Although the difference of two functions is only a operator (``````), UniXcoder can distinguish them.

# Normalize embedding
norm_max_func_embedding = torch.nn.functional.normalize(max_func_embedding, p=2, dim=1)
norm_min_func_embedding = torch.nn.functional.normalize(min_func_embedding, p=2, dim=1)
norm_nl_embedding = torch.nn.functional.normalize(nl_embedding, p=2, dim=1)

max_func_nl_similarity = torch.einsum("ac,bc->ab",norm_max_func_embedding,norm_nl_embedding)
min_func_nl_similarity = torch.einsum("ac,bc->ab",norm_min_func_embedding,norm_nl_embedding)

print(max_func_nl_similarity)
print(min_func_nl_similarity)

tensor([[0.3002]], device='cuda:0', grad_fn=)
tensor([[0.1881]], device='cuda:0', grad_fn=)

3. Decoder-only Mode

For decoder-only mode, we give an example of code completion.

context = """
def f(data,file_path):
    # write json data into file_path in python language
"""
tokens_ids = model.tokenize([context],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
prediction_ids = model.generate(source_ids, decoder_only=True, beam_size=3, max_length=128)
predictions = model.decode(prediction_ids)
print(context+predictions[0][0])

def f(data,file_path):
    # write json data into file_path in python language
    data = json.dumps(data)
    with open(file_path, 'w') as f:
        f.write(data)

4. Encoder-Decoder Mode

For encoder-decoder mode, we give two examples including: function name prediction, API recommendation, code summarization.

1) Function Name Prediction

context = """
def (data,file_path):
    data = json.dumps(data)
    with open(file_path, 'w') as f:
        f.write(data)
"""
tokens_ids = model.tokenize([context],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
prediction_ids = model.generate(source_ids, decoder_only=False, beam_size=3, max_length=128)
predictions = model.decode(prediction_ids)
print([x.replace("","").strip() for x in predictions[0]])

['write_json', 'write_file', 'to_json']

2) API Recommendation

context = """
def write_json(data,file_path):
    data = (data)
    with open(file_path, 'w') as f:
        f.write(data)
"""
tokens_ids = model.tokenize([context],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
prediction_ids = model.generate(source_ids, decoder_only=False, beam_size=3, max_length=128)
predictions = model.decode(prediction_ids)
print([x.replace("","").strip() for x in predictions[0]])

['json.dumps', 'json.loads', 'str']

3) Code Summarization

context = """
#
def write_json(data,file_path):
    data = json.dumps(data)
    with open(file_path, 'w') as f:
        f.write(data)
"""
tokens_ids = model.tokenize([context],max_length=512,mode="")
source_ids = torch.tensor(tokens_ids).to(device)
prediction_ids = model.generate(source_ids, decoder_only=False, beam_size=3, max_length=128)
predictions = model.decode(prediction_ids)
print([x.replace("","").strip() for x in predictions[0]])

['W