Duplicate from codeparrot/code-complexity-predictor

Co-authored-by: loubna ben allal <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: BigO
+emoji: ⏱️
+colorFrom: pink
+colorTo: blue
+sdk: gradio
+sdk_version: 3.21.0
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: codeparrot/code-complexity-predictor
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,48 @@
+import gradio as gr
+from datasets import ClassLabel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+
+
+title = "BigO"
+description = "In this space we predict the complexity of Java code with [UniXcoder-java-complexity-prediction](https://huggingface.co/codeparrot/unixcoder-java-complexity-prediction),\
+    a multilingual model for code, fine-tuned on [CodeComplex](https://huggingface.co/datasets/codeparrot/codecomplex), a dataset for complexity prediction of Java code."
+
+#add examples
+example = [['int n = 1000;\nSystem.out.println("Hey - your input is: " + n);'],
+    ['class GFG {\n \n    public static void main(String[] args)\n    {\n        int i, n = 8;\n        for (i = 1; i <= n; i++) {\n            System.out.printf("Hello World !!!\n");\n        }\n    }\n}'],
+    ['import java.io.*;\nimport java.util.*;\n\npublic class C125 {\n\tpublic static void main(String[] args) throws IOException {\n\t\tBufferedReader r = new BufferedReader(new InputStreamReader(System.in));\n\t\tString s = r.readLine();\n\t\tint n = new Integer(s);\n\t\tSystem.out.println("0 0 "+n);\n\t}\n}\n']]
+
+# model to be changed to the finetuned one
+tokenizer = AutoTokenizer.from_pretrained("codeparrot/unixcoder-java-complexity-prediction")
+model = AutoModelForSequenceClassification.from_pretrained("codeparrot/unixcoder-java-complexity-prediction", num_labels=7)
+
+def get_label(output):
+    label = int(output[-1])
+    labels = ClassLabel(num_classes=7, names=['constant', 'cubic', 'linear', 'logn', 'nlogn', 'np', 'quadratic'])
+    return labels.int2str(label)
+    
+def complexity_estimation(gen_prompt):
+    pipe = pipeline("text-classification", model=model, tokenizer=tokenizer)
+    output = pipe(gen_prompt)[0]
+    # add label conversion to class
+    label = get_label(output['label'])
+    score = output['score']
+    return label, score
+
+
+iface = gr.Interface(
+    fn=complexity_estimation, 
+    inputs=[
+        gr.Code(lines=10, language="java", label="Input code"),
+    ],
+    outputs=[
+    gr.Textbox(label="Predicted complexity", lines=1) ,
+    gr.Textbox(label="Corresponding probability", lines=1) ,
+],
+    examples=example,
+    layout="vertical",
+    theme="darkpeach",
+    description=description,
+    title=title
+)
+iface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+transformers==4.19.0
+torch==1.11.0
+datasets