Microbiome Questions

#!/usr/bin/env bash
num_iter=10
prompt="Please generate a random research question about the microbiome. Output only the question. No extra stuff."
echo "The prompt is: $prompt"
echo

for (( i = 0; i < $num_iter; i++ ))
do
    chatbot geminifl "$prompt"
    echo "$i" >&2
    echo
done

./iterative_monolog.sh > your_output_file.txt

#!/usr/bin/env python3

"""
question_map_umap_cluster.py

Visualise research questions **and** colour points by clustering performed *on
the 2‑D UMAP coordinates* (so what you see is what was clustered).

Pipeline
--------
1. Split blank‑line–separated questions.
2. Embed with Sentence‑Transformers.
3. UMAP → 2‑D.
4. **K‑means on the UMAP coords** (k = 5 by default).
5. Plot with Plotly; hover shows cluster + wrapped question.

Usage
-----
```bash
python question_map_umap_cluster.py            # sample questions
python question_map_umap_cluster.py my_qs.txt  # your own list
```

Dependencies
------------
```bash
pip install sentence-transformers umap-learn scikit-learn plotly pandas
```
"""

import sys
from pathlib import Path
import textwrap
from typing import List

import pandas as pd
import plotly.express as px
from sentence_transformers import SentenceTransformer
import umap
from sklearn.cluster import KMeans

# ── sample questions ────────────────────────────────────────────────────
TEXT = """
How do early-life microbial colonizers influence the development of allergen sensitization in infants?

How does the gut microbiome composition in elderly individuals correlate with their susceptibility to seasonal influenza infections?

How do changes in gut microbiome composition influence cognitive function and mood regulation in aging adults?

How does the gut microbiome composition of endurance athletes influence their response to carbohydrate loading protocols?

How does the gut microbiome composition of astronauts change during long-duration space missions and what are the potential implications for their immune function and nutrient absorption upon return to Earth?
"""

# ── constants / tunables ───────────────────────────────────────────────
MODEL_NAME = "all-mpnet-base-v2"
WRAP_WIDTH = 80
UMAP_RANDOM_STATE = 42

N_CLUSTERS = 20          # k for kmeans

# ── helpers ─────────────────────────────────────────────────────────────

split_by_blank = lambda t: [p.strip() for p in t.strip().split("\n\n") if p.strip()]


def embed(texts: List[str]):
    return SentenceTransformer(MODEL_NAME).encode(texts, convert_to_numpy=True, normalize_embeddings=True)


def umap_2d(embeddings):
    reducer = umap.UMAP(n_components=2, metric="cosine", random_state=UMAP_RANDOM_STATE)
    return reducer.fit_transform(embeddings)

def cluster_coords(coords):
    return KMeans(n_clusters=N_CLUSTERS, random_state=UMAP_RANDOM_STATE, n_init="auto").fit_predict(coords)

def wrap(text: str) -> str:
    return textwrap.fill(text, width=WRAP_WIDTH).replace("\n", "<br>")


def build_df(questions, coords, labels):
    df = pd.DataFrame({"x": coords[:, 0], "y": coords[:, 1],
                       "question": questions, "cluster": labels})
    df = df.reset_index(drop=True)
    df["cluster_label"] = df["cluster"].apply(lambda n: f"C{n}")
    df["hover"] = df["question"].apply(wrap) # control: this does not jumble shit
    return df

def plot(df):
    fig = px.scatter(
        df,
        x="x",
        y="y",
        color="cluster_label",          # keeps the colours
        custom_data=["hover"],          # let PX attach the right slice to each trace
        template="plotly_white",
        title="UMAP of research questions (clustered on UMAP coords)",
    )

    fig.update_traces(
        marker=dict(size=9, opacity=0.8),
        hovertemplate="%{customdata[0]}<extra></extra>",
    )
    fig.write_html("umap_questions_with_clustering.html", auto_open=True)
# ── main ────────────────────────────────────────────────────────────────

def main():
    text_source = Path(sys.argv[1]).read_text(encoding="utf-8") if len(sys.argv) > 1 else TEXT
    questions = split_by_blank(text_source)
    if not questions:
        sys.exit("No questions found.")

    print(f"{len(questions)} questions → embed → UMAP → K‑means (on coords) → plot …")

    emb = embed(questions)
    coords = umap_2d(emb)
    labels = cluster_coords(coords)

    df = build_df(questions, coords, labels)
    plot(df)

    # Output
    emb = pd.DataFrame(emb)
    emb.columns = [f"emb_{i + 1}" for i in range(emb.shape[1])]
    emb.to_csv("question_map_embeddings.csv")
    df.to_csv("question_map_with_clustering_df.csv")


if __name__ == "__main__":
    main()

#!/usr/bin/env python3

# Libraries
import pandas as pd
import plotly.express as px
import textwrap

def wrap(text: str) -> str:
    return textwrap.fill(text, width=80).replace("\n", "<br>")

def main():
    df = pd.read_csv("question_map_with_labeled_clusters.csv")
    df["meta_question_wrap"] = df["meta_question"].apply(wrap)

    fig = px.scatter(df,
                     x = "x",
                     y = "y",
                     color = "cluster_label",
                     hover_data = {"x": False, "y": False, "hover": True, "cluster_label": True, "meta_question_wrap": True})

    fig.update_layout(legend=dict(
        yanchor="top",
        y=0.99,
        xanchor="left",
        x=0.01,
    ))

    fig.update_traces(
        hoverlabel = dict(font_size=20),
    )

    fig.write_html("umap_questions_with_mq.html", auto_open=True)

if __name__ == "__main__":
    main()