Upload 3 files

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from main2 import search_trials  # Importing from main2.py
+
+def run_search(age, sex, state, keywords):
+    results = search_trials(
+        user_age=age,
+        user_sex=sex,
+        user_state=state,
+        user_keywords=keywords
+    )
+    return results
+
+with gr.Blocks() as demo:
+    gr.Markdown("#  Clinical Trials Search Tool")
+    gr.Markdown(
+        "Find **recruiting US clinical trials** that match your **age**, **sex**, "
+        "**state**, and optional **keywords**."
+    )
+
+    with gr.Row():
+        age_input = gr.Number(label="Your Age", value=30)
+        sex_input = gr.Dropdown(["Male", "Female"], label="Sex", value="Male")
+
+    with gr.Row():
+        state_input = gr.Textbox(label="State (full name or abbreviation)", placeholder="e.g., California")
+        keywords_input = gr.Textbox(label="Keywords (comma separated)", placeholder="e.g., cancer, diabetes")
+
+    search_btn = gr.Button("Search Trials")
+
+    output_table = gr.Dataframe(label="Matching Trials", interactive=False)
+
+    search_btn.click(
+        fn=run_search,
+        inputs=[age_input, sex_input, state_input, keywords_input],
+        outputs=output_table
+    )
+
+if __name__ == "__main__":
+    demo.launch()

main2.py

@@ -0,0 +1,59 @@
+import pandas as pd
+
+def search_trials(user_age, user_sex, user_state, user_keywords, csv_path="clinical_trials_cleaned_merged.csv"):
+    """
+    Search for recruiting US clinical trials matching the user's demographics & optional keywords.
+    Returns ALL available columns from the dataset.
+    """
+
+    # === Load dataset ===
+    df = pd.read_csv(csv_path)
+
+    # Drop missing critical columns
+    df = df.dropna(subset=["MinimumAge", "MaximumAge", "Sex", "OverallStatus"])
+
+    # Keep only US & recruiting trials
+    df = df[df["LocationCountry"] == "United States"]
+    df = df[df["OverallStatus"].str.lower() == "recruiting"]
+
+    # Convert ages to numeric
+    def parse_age(age_str):
+        if pd.isnull(age_str):
+            return None
+        parts = str(age_str).split()
+        try:
+            return int(parts[0])
+        except:
+            return None
+
+    df["MinAgeNum"] = df["MinimumAge"].apply(parse_age)
+    df["MaxAgeNum"] = df["MaximumAge"].apply(parse_age)
+
+    # Prepare user's keywords list
+    if isinstance(user_keywords, str):
+        keywords = [k.strip().lower() for k in user_keywords.split(",") if k.strip()]
+    elif isinstance(user_keywords, list):
+        keywords = [str(k).strip().lower() for k in user_keywords if str(k).strip()]
+    else:
+        keywords = []
+
+    # === Create masks ===
+    sex_mask = df["Sex"].str.lower().isin([str(user_sex).lower(), "all"])
+    age_mask = (df["MinAgeNum"] <= int(user_age)) & (df["MaxAgeNum"] >= int(user_age))
+    state_mask = df["LocationState"].str.lower() == str(user_state).lower()
+
+    if keywords:
+        def row_matches_any_keyword(row):
+            row_as_str = " ".join(str(x).lower() for x in row.values if pd.notnull(x))
+            return any(k in row_as_str for k in keywords)
+        keyword_mask = df.apply(row_matches_any_keyword, axis=1)
+    else:
+        keyword_mask = True
+
+    # Apply all filters and return ALL columns
+    filtered_df = df[sex_mask & age_mask & state_mask & keyword_mask].reset_index(drop=True)
+
+    # Drop helper numeric age cols if you don’t want them visible
+    filtered_df = filtered_df.drop(columns=["MinAgeNum", "MaxAgeNum"], errors="ignore")
+
+    return filtered_df

requirements.txt

@@ -0,0 +1,144 @@
+aiofiles==24.1.0
+aioitertools==0.12.0
+annotated-types==0.7.0
+anyio==4.10.0
+appnope==0.1.4
+asttokens==3.0.0
+attrs==25.3.0
+audioop-lts==0.2.2
+bcrypt==4.3.0
+bibtexparser==1.4.3
+boto3==1.40.5
+botocore==1.40.5
+Brotli==1.1.0
+certifi==2025.8.3
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+comm==0.2.3
+contourpy==1.3.3
+cryptography==45.0.6
+cycler==0.12.1
+debugpy==1.8.16
+decorator==5.2.1
+dnspython==2.7.0
+emmet-core==0.84.9
+executing==2.2.0
+fastapi==0.116.1
+ffmpy==0.6.1
+filelock==3.18.0
+fonttools==4.59.0
+fsspec==2025.7.0
+gradio==5.42.0
+gradio_client==1.11.1
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.7
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.34.4
+idna==3.10
+invoke==2.2.0
+ipykernel==6.30.1
+ipython==9.4.0
+ipython_pygments_lexers==1.1.1
+jedi==0.19.2
+Jinja2==3.1.6
+jmespath==1.0.1
+joblib==1.5.1
+jsonlines==4.0.0
+jsonschema==4.25.0
+jsonschema-specifications==2025.4.1
+jupyter_client==8.6.3
+jupyter_core==5.8.1
+kiwisolver==1.4.8
+latexcodec==3.0.1
+maggma==0.71.5
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.5
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mongomock==4.3.0
+monty==2025.3.3
+mp-api==0.45.8
+mpmath==1.3.0
+msgpack==1.1.1
+narwhals==2.0.1
+nest-asyncio==1.6.0
+networkx==3.5
+numpy==2.3.2
+orjson==3.11.1
+packaging==25.0
+palettable==3.3.3
+pandas==2.3.1
+paramiko==4.0.0
+parso==0.8.4
+pexpect==4.9.0
+pillow==11.3.0
+platformdirs==4.3.8
+plotly==6.2.0
+prompt_toolkit==3.0.51
+psutil==7.0.0
+ptyprocess==0.7.0
+PubChemPy==1.0.4
+pure_eval==0.2.3
+pybtex==0.25.1
+pycparser==2.22
+pydantic==2.11.7
+pydantic-settings==2.10.1
+pydantic_core==2.33.2
+pydash==8.0.5
+pydub==0.25.1
+Pygments==2.19.2
+pymatgen==2025.6.14
+pymongo==4.10.1
+PyNaCl==1.5.0
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.1
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+pyzmq==27.0.1
+rdkit==2025.3.5
+referencing==0.36.2
+requests==2.32.4
+rich==14.1.0
+rpds-py==0.27.0
+ruamel.yaml==0.18.14
+ruamel.yaml.clib==0.2.12
+ruff==0.12.8
+s3transfer==0.13.1
+safehttpx==0.1.6
+scikit-learn==1.7.1
+scipy==1.16.1
+semantic-version==2.10.0
+sentinels==1.0.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+smart_open==7.3.0.post1
+sniffio==1.3.1
+spglib==2.6.0
+sshtunnel==0.4.0
+stack-data==0.6.3
+starlette==0.47.2
+sympy==1.14.0
+tabulate==0.9.0
+threadpoolctl==3.6.0
+tomlkit==0.13.3
+tornado==6.5.1
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+tzdata==2025.2
+uncertainties==3.2.3
+urllib3==2.5.0
+uvicorn==0.35.0
+wcwidth==0.2.13
+websockets==15.0.1
+wrapt==1.17.2
+xgboost==3.0.3