Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1,214 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+.venv2
+.venv3
+.venv*
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+**/.DS_Store
+
+old_stuff/
+
+**/data/**/*.*
+!.gitkeep
+
+# VisualStudioCode.gitignore
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+# macOS.gitignore
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+logs/

README.md

@@ -1,12 +1,6 @@
 ---
-title: Embeddings UBalt
-emoji: 😻
-colorFrom: blue
-colorTo: blue
+title: Embeddings-UBalt
+app_file: emb_sim.py
 sdk: gradio
 sdk_version: 4.42.0
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

emb_sim.py

@@ -0,0 +1,158 @@
+import gradio as gr
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from matplotlib.colors import LinearSegmentedColormap
+from sklearn.metrics.pairwise import cosine_similarity
+from openai import OpenAI, AuthenticationError, RateLimitError
+from dotenv import load_dotenv
+import os
+
+
+load_dotenv()
+openai_api_key = os.getenv("OPENAI_API_KEY")
+oai_client = OpenAI(api_key=openai_api_key)
+
+
+def get_openai_embedding(word):
+    response = oai_client.embeddings.create(input=word, model="text-embedding-3-small")
+    return response.data[0].embedding
+
+
+def calculate_embeddings(words):
+    # Get word embeddings
+    embeddings = [get_openai_embedding(word) for word in words]
+    return embeddings
+
+
+def process_array(arr):
+    # Ensure the input is a square array
+    if arr.shape[0] != arr.shape[1]:
+        raise ValueError("Input must be a square array")
+
+    n = arr.shape[0]
+
+    # Step 1: Keep only the upper triangle (excluding diagonal)
+    upper_triangle = np.triu(arr, k=1)
+
+    # Step 2: Reverse horizontally
+    reversed_upper_triangle = np.fliplr(upper_triangle)
+
+    # Step 3: Drop the final row and column
+    result = reversed_upper_triangle[:-1, :-1]
+
+    # Step 4: Mask the zeros
+    masked_result = np.ma.masked_where(result == 0, result)
+
+    return masked_result
+
+
+def plot_heatmap(masked_result, l1: list[str]):
+    n, _ = masked_result.shape
+
+    # Create the heatmap
+    fig, ax = plt.subplots(
+        figsize=(12, 10)
+    )  # Increased figure size for better visibility
+
+    # Create a custom colormap
+    colors = ["darkred", "lightgray", "dodgerblue"]
+    n_bins = 100
+    cmap = LinearSegmentedColormap.from_list("custom", colors, N=n_bins)
+    cmap.set_bad("white")  # Set color for masked values (zeros) to white
+
+    # Plot the heatmap
+    im = ax.imshow(masked_result, cmap=cmap, vmin=-1, vmax=1)
+
+    # Add text annotations
+    for i in range(n):
+        for j in range(n):
+            if not np.ma.is_masked(masked_result[i, j]):
+                text = ax.text(
+                    j,
+                    i,
+                    f"{masked_result[i, j]:.2f}",
+                    ha="center",
+                    va="center",
+                    color="black",
+                )
+
+    # Set y and x axis labels
+    ax.set_yticks(range(n))
+    ax.set_yticklabels(l1[:-1])
+    ax.set_xticks(range(n))
+    ax.set_xticklabels(reversed(l1[1:]))
+
+    # Move x-axis to the top
+    ax.xaxis.tick_top()
+    ax.xaxis.set_label_position("top")
+
+    # Rotate x-axis labels for better readability
+    plt.setp(ax.get_xticklabels(), rotation=45, ha="left", rotation_mode="anchor")
+
+    # Add colorbar
+    cbar = plt.colorbar(im)
+    cbar.set_ticks([-1, 0, 1])
+    cbar.set_ticklabels(["-1", "0", "1"])
+
+    # Add title
+    plt.title("Correlation Heatmap", pad=20)
+
+    # Adjust layout and display the plot
+    plt.tight_layout()
+    return fig
+
+
+def plot_pca(embeddings, words):
+    fig, ax = plt.subplots(figsize=(12, 10))
+    pca = PCA(n_components=2)
+    embeddings_2d = pca.fit_transform(embeddings)
+
+    fig, ax = plt.subplots(figsize=(10, 8))
+    ax.scatter(embeddings_2d[:, 0], embeddings_2d[:, 1])
+
+    for i, word in enumerate(words):
+        ax.annotate(word, (embeddings_2d[i, 0], embeddings_2d[i, 1]))
+
+    ax.set_title("PCA of Word Embeddings")
+    ax.set_xlabel("First Principal Component")
+    ax.set_ylabel("Second Principal Component")
+    plt.tight_layout()
+    return fig
+
+
+def word_similarity_heatmap(input_text):
+    words = [word.strip() for word in input_text.split(",")]
+
+    if len(words) < 2:
+        return "Please enter at least two words."
+
+    try:
+        embeddings = calculate_embeddings(words)
+        similarities = cosine_similarity(embeddings)
+        new_array = process_array(similarities)
+        heatmap = plot_heatmap(new_array, words)
+        pca_plot = plot_pca(embeddings, words)
+        return heatmap, pca_plot
+        # return heatmap
+    except AuthenticationError as e:
+        print("OpenAI API key is invalid. Please check your API key.")
+        raise e
+    except RateLimitError as e:
+        print("OpenAI API rate limit exceeded. Please try again later.")
+        raise e
+    except Exception as e:
+        print(f"An error occurred: {str(e)}")
+        raise e
+
+
+iface = gr.Interface(
+    fn=word_similarity_heatmap,  # _and_pca,
+    inputs=gr.Textbox(lines=2, placeholder="Enter words separated by commas"),
+    outputs=[gr.Plot(label="Similarity Heatmap"), gr.Plot(label="PCA Plot")],
+    title="Word Similarity Heatmap and PCA Plot using OpenAI Embeddings",
+    description="Enter a list of words separated by commas. The app will calculate the cosine similarity between their OpenAI embeddings, display a compact heatmap of the upper triangle similarities, and show a PCA plot of the embeddings.",
+)
+
+# Launch the app
+iface.launch(share=True)

requirements.txt

@@ -0,0 +1,66 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.4.0
+certifi==2024.7.4
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+distro==1.9.0
+fastapi==0.112.2
+ffmpy==0.4.0
+filelock==3.15.4
+fonttools==4.53.1
+fsspec==2024.6.1
+gradio==4.42.0
+gradio_client==1.3.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.24.6
+idna==3.8
+importlib_resources==6.4.4
+Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.2
+mdurl==0.1.2
+numpy==2.1.0
+openai==1.42.0
+orjson==3.10.7
+packaging==24.1
+pandas==2.2.2
+pillow==10.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.8.0
+ruff==0.6.2
+scikit-learn==1.5.1
+scipy==1.14.1
+seaborn==0.13.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.38.2
+threadpoolctl==3.5.0
+tomlkit==0.12.0
+tqdm==4.66.5
+typer==0.12.5
+typing_extensions==4.12.2
+tzdata==2024.1
+urllib3==2.2.2
+uvicorn==0.30.6
+websockets==12.0