initial commit

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.10.14-slim
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+COPY . /app
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README.md

@@ -6,6 +6,7 @@ colorTo: indigo
 sdk: docker
 pinned: false
 short_description: Interactive web application to get insights from reviews
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+datasets:
+- Jbddai/customer_reviews
+app_port: 7860
+---

app.py

@@ -0,0 +1,322 @@
+from dash import Dash, dcc, html, Input, Output, State
+import dash.dependencies as dd
+import plotly.express as px
+import pandas as pd
+
+# Load DataFrame from CSV
+df_result_bad_distil_2 = df = pd.read_csv(
+    "hf://datasets/Jbddai/customer_reviews/bad_distil_2_with_cluster_labels_cleaned_company.csv"
+)
+df_result_good_distil_2 = df = pd.read_csv(
+    "hf://datasets/Jbddai/customer_reviews/good_distil_2_with_cluster_labels_cleaned_company.csv"
+)
+
+
+def preprocess_data_for_slider_marks(df):
+    min_label = df["labels"].min()
+    max_label = df["labels"].max()
+    min_cluster_rank = df["cluster_rank"].min()
+    max_cluster_rank = df["cluster_rank"].max()
+
+    label_marks = {i: str(i + 1) for i in range(min_label, max_label + 1, 10)}
+    cluster_rank_marks = {i: str(i + 1) for i in range(min_cluster_rank, max_cluster_rank + 1, 10)}
+
+    return label_marks, min_label, max_label, cluster_rank_marks, min_cluster_rank, max_cluster_rank
+
+
+label_marks, min_label, max_label, cluster_rank_marks, min_cluster_rank, max_cluster_rank = (
+    preprocess_data_for_slider_marks(df_result_good_distil_2)
+)
+
+sentiment_options = [
+    {"label": "gut", "value": "gut"},
+    {"label": "schlecht", "value": "schlecht"},
+]
+
+app = Dash(__name__)
+
+app.layout = html.Div(
+    [
+        html.Div(
+            [
+                html.H4("Interactive Plot of Customer Reviews"),
+                html.Div(
+                    [
+                        html.P("Select sentiment:"),
+                        dcc.Dropdown(
+                            id="sentiment-dropdown",
+                            options=sentiment_options,
+                            value="gut",
+                            style={"width": "50%", "margin": "auto"},
+                            clearable=False,
+                            multi=False,
+                        ),
+                    ],
+                    style={"width": "50%", "margin": "auto"},
+                ),
+                html.Div(
+                    [
+                        html.P("Select range of labels:"),
+                        dcc.RangeSlider(
+                            id="label-range-slider",
+                            min=df_result_good_distil_2["labels"].min(),
+                            max=df_result_good_distil_2["labels"].max(),
+                            step=1,
+                            value=[
+                                df_result_good_distil_2["labels"].min(),
+                                df_result_good_distil_2["labels"].max(),
+                            ],
+                            marks={
+                                i: str(i + 1)
+                                for i in range(
+                                    df_result_good_distil_2["labels"].min(),
+                                    df_result_good_distil_2["labels"].max() + 1,
+                                    10,
+                                )
+                            },
+                            tooltip={"always_visible": True, "placement": "bottom"},
+                        ),
+                        html.Button("Reset Range", id="reset-button", n_clicks=0),
+                    ],
+                    style={"width": "50%", "margin": "auto"},
+                ),
+                html.Div(
+                    [
+                        html.P("Select range of cluster by rank/popularity (by number of reviews descending):"),
+                        dcc.RangeSlider(
+                            id="cluster-rank-slider",
+                            min=df_result_good_distil_2["cluster_rank"].min(),
+                            max=df_result_good_distil_2["cluster_rank"].max(),
+                            step=1,
+                            value=[
+                                df_result_good_distil_2["cluster_rank"].min(),
+                                df_result_good_distil_2["cluster_rank"].max(),
+                            ],
+                            marks={
+                                i: str(i + 1)
+                                for i in range(
+                                    df_result_good_distil_2["cluster_rank"].min(),
+                                    df_result_good_distil_2["cluster_rank"].max() + 1,
+                                    10,
+                                )
+                            },
+                            tooltip={"always_visible": True, "placement": "bottom"},
+                        ),
+                        html.Button("Reset Cluster Rank", id="reset-cluster-button", n_clicks=0),
+                    ],
+                    style={"width": "50%", "margin": "auto"},
+                ),
+                html.Div(
+                    [
+                        html.P("Show Cluster Labels:"),
+                        dcc.Checklist(
+                            id="show-cluster-labels",
+                            options=[{"label": "Show", "value": "on"}],
+                            value=["off"],
+                        ),
+                    ],
+                    style={"width": "50%", "margin": "auto"},
+                ),
+            ],
+            style={"position": "relative", "zIndex": "1001", "marginBottom": "20px"},
+        ),
+        dcc.Graph(
+            id="scatter-plot",
+            style={
+                "height": "80vh",
+                "width": "90vw",
+                "position": "relative",
+                "zIndex": "999",
+            },
+        ),
+        html.Div(
+            [html.Button("Generate LLM Prompt from current selection", id="generate-cluster-button", n_clicks=0)],
+            style={"width": "50%", "margin": "auto"},
+        ),
+        html.Div(
+            [
+                html.P("Prompt for LLM:"),
+                dcc.Textarea(
+                    id="cluster-text-output",
+                    style={"width": "100%", "height": "200px", "display": "none"},
+                    value="",
+                ),
+            ],
+            style={"width": "50%", "margin": "auto"},
+        ),
+    ]
+)
+
+
+@app.callback(
+    Output("scatter-plot", "figure"),
+    [
+        Input("label-range-slider", "value"),
+        Input("cluster-rank-slider", "value"),
+        Input("sentiment-dropdown", "value"),
+        Input("show-cluster-labels", "value"),
+    ],
+)
+def update_scatter_plot(label_range, cluster_rank_range, selected_sentiment, show_cluster_labels):
+    show_labels = "on" in show_cluster_labels
+
+    if selected_sentiment == "gut":
+        df_filtered = df_result_good_distil_2
+    else:
+        df_filtered = df_result_bad_distil_2
+
+    df_filtered = df_filtered[
+        (df_filtered["labels"].between(label_range[0], label_range[1]))
+        & (df_filtered["cluster_rank"].between(cluster_rank_range[0], cluster_rank_range[1]))
+    ]
+
+    outliers = df_filtered[df_filtered.labels == -1]
+    clustered = df_filtered[df_filtered.labels != -1]
+
+    fig = px.scatter(
+        clustered,
+        x="x",
+        y="y",
+        hover_data=[
+            "summary_good_bad",
+            "sentiment",
+            "cluster_rank",
+            "cluster_count",
+            "clean_review_br",
+        ],
+        hover_name="cluster_label",
+        color="labels",
+        color_continuous_scale="rainbow",
+        opacity=0.7,
+    )
+
+    if show_labels:
+        centroids = clustered.groupby("labels", sort=False).agg(
+            {
+                "x": "mean",
+                "y": "mean",
+                "cluster_label": "first",
+                "cluster_count": "count",
+            }
+        )
+        for row in centroids.itertuples():
+            fig.add_annotation(
+                x=row.x,
+                y=row.y,
+                text=f"{row.cluster_label}, #reviews: {row.cluster_count}",
+                showarrow=False,
+            )
+
+    fig.add_scatter(
+        x=outliers["x"],
+        y=outliers["y"],
+        mode="markers",
+        marker=dict(color="lightgray", opacity=0.5, size=5.0),
+        name="No cluster",
+        selectedpoints=False,
+        hoverinfo="skip",
+    )
+
+    fig.update_layout(coloraxis_colorbar=dict(len=0.9, x=1.0), height=600)
+    fig.update_traces(marker=dict(size=3), selector=dict(mode="markers"))
+
+    return fig
+
+
+@app.callback(
+    [
+        Output("label-range-slider", "marks"),
+        Output("label-range-slider", "min"),
+        Output("label-range-slider", "max"),
+        Output("cluster-rank-slider", "marks"),
+        Output("cluster-rank-slider", "min"),
+        Output("cluster-rank-slider", "max"),
+    ],
+    [Input("sentiment-dropdown", "value")],
+)
+def update_slider_marks(selected_sentiment):
+    if selected_sentiment == "gut":
+        df_filtered = df_result_good_distil_2
+    else:
+        df_filtered = df_result_bad_distil_2
+
+    label_marks, min_label, max_label, cluster_rank_marks, min_cluster_rank, max_cluster_rank = (
+        preprocess_data_for_slider_marks(df_filtered)
+    )
+
+    return (
+        label_marks,
+        min_label,
+        max_label,
+        cluster_rank_marks,
+        min_cluster_rank,
+        max_cluster_rank,
+    )
+
+
+@app.callback(
+    Output("label-range-slider", "value"),
+    [Input("reset-button", "n_clicks")],
+    [State("label-range-slider", "min"), State("label-range-slider", "max")],
+)
+def reset_label_slider(n_clicks, min_val, max_val):
+    return [min_val, max_val]
+
+
+@app.callback(
+    Output("cluster-rank-slider", "value"),
+    [Input("reset-cluster-button", "n_clicks")],
+    [State("cluster-rank-slider", "min"), State("cluster-rank-slider", "max")],
+)
+def reset_cluster_slider(n_clicks, min_val, max_val):
+    return [min_val, max_val]
+
+
+@app.callback(
+    Output("cluster-text-output", "style"),
+    [Input("generate-cluster-button", "n_clicks")],
+)
+def show_cluster_text_output(n_clicks):
+    if n_clicks > 0:
+        return {"width": "100%", "height": "200px", "display": "block"}
+    else:
+        return {"width": "100%", "height": "200px", "display": "none"}
+
+
+@app.callback(
+    Output("cluster-text-output", "value"),
+    [Input("generate-cluster-button", "n_clicks")],
+    [State("cluster-rank-slider", "value"), State("sentiment-dropdown", "value")],
+)
+def update_cluster_text_output(n_clicks, cluster_rank_range, selected_sentiment):
+    if n_clicks > 0:
+        if selected_sentiment == "gut":
+            df_text_outp = df_result_good_distil_2
+        else:
+            df_text_outp = df_result_bad_distil_2
+
+        df_text_outp = df_text_outp[
+            (df_text_outp["cluster_rank"] <= cluster_rank_range[1])
+            & (df_text_outp["cluster_rank"] >= cluster_rank_range[0])
+        ]
+
+        df_text_outp["summary_good_bad"] = df_text_outp["summary_good_bad"].fillna("").astype(str)
+
+        sampled_data = df_text_outp.sample(frac=0.1, random_state=42)
+
+        grouped_data = (
+            sampled_data.groupby("cluster_label", sort=False)["summary_good_bad"].agg("\n".join).reset_index()
+        )
+
+        prompt_instruction = """Analysiere die nach ### folgenden CLUSTER "Clustertitel", die einzelene Bestandteile von Bewertungen erhalten\nund leite pro Cluster eine Business Massnahme ab um das Hauptproblem des Clusters zu lösen oder zu Verbessern.\nGib das Cluster mit seinem "Clustertitel" sowie die dazugehörige Maßnahme zurück.\n###"""
+
+        cluster_texts = prompt_instruction + "\n\n".join(
+            f"\nCLUSTER - {row['cluster_label']}\n{row['summary_good_bad']}" for _, row in grouped_data.iterrows()
+        )
+        return cluster_texts
+    else:
+        return ""
+
+
+if __name__ == "__main__":
+    app.run_server(debug=True, host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,5 @@
+dash==2.15.0
+fsspec==2024.2.0
+huggingface-hub==0.20.3
+pandas==2.2.0
+plotly==5.18.0