Upload 2 files

app.py

@@ -0,0 +1,156 @@
+\
+import os
+import io
+import pandas as pd
+import numpy as np
+import gradio as gr
+
+# Matplotlib only (no seaborn), single chart per plot, no explicit colors
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+
+DEFAULT_CSV = "Trend_of_Top_10_Hard_Skills.csv"  # Place at repo root
+
+def load_dataframe(file):
+    """Load CSV from uploaded file or the default CSV on repo root"""
+    if file is not None:
+        return pd.read_csv(file.name if hasattr(file, "name") else file)
+    if os.path.exists(DEFAULT_CSV):
+        return pd.read_csv(DEFAULT_CSV)
+    raise gr.Error("No CSV provided and default file not found. Please upload a CSV.")
+
+def prepare_dataframe(df):
+    """
+    Expect columns: YearMonth, <skill1>, <skill2>, ...
+    YearMonth as YYYY-MM, convert to datetime for sorting, back to string for ticks.
+    """
+    if "YearMonth" not in df.columns:
+        raise gr.Error("CSV must have a 'YearMonth' column.")
+    # Parse YearMonth to datetime (coerce errors to NaT)
+    dt = pd.to_datetime(df["YearMonth"], format="%Y-%m", errors="coerce")
+    # If parsing fails, try general parse
+    if dt.isna().any():
+        dt = pd.to_datetime(df["YearMonth"], errors="coerce")
+    df = df.copy()
+    df["_dt"] = dt
+    df = df.sort_values("_dt")
+    # Coerce numeric columns
+    for c in df.columns:
+        if c not in ["YearMonth", "_dt"]:
+            df[c] = pd.to_numeric(df[c], errors="coerce")
+    return df
+
+def list_skill_columns(df):
+    return [c for c in df.columns if c not in ["YearMonth", "_dt"]]
+
+def apply_smoothing(series, window):
+    if window and window > 1:
+        return series.rolling(window=window, min_periods=1, center=False).mean()
+    return series
+
+def normalize_series(series, mode):
+    if mode == "none":
+        return series
+    s = series.copy()
+    if mode == "min-max (per skill)":
+        mn, mx = s.min(), s.max()
+        if mx > mn:
+            return (s - mn) / (mx - mn)
+        else:
+            return s.fillna(0.0)
+    if mode == "z-score (per skill)":
+        mu, sd = s.mean(), s.std(ddof=0)
+        if sd > 0:
+            return (s - mu) / sd
+        else:
+            return s.fillna(0.0)
+    return series
+
+def plot_lines(df, selected_skills, smoothing_window, normalize_mode, show_markers, y_label):
+    if not selected_skills:
+        raise gr.Error("Please select at least one skill.")
+
+    # Prepare x
+    x_dt = df["_dt"]
+    x_labels = df["YearMonth"].astype(str).tolist()
+
+    # Create single chart
+    fig = plt.figure(figsize=(10, 5.5))
+    ax = fig.add_subplot(111)
+
+    for skill in selected_skills:
+        if skill not in df.columns:
+            continue
+        y = df[skill]
+        y = apply_smoothing(y, smoothing_window)
+        y = normalize_series(y, normalize_mode)
+        if show_markers:
+            ax.plot(x_dt, y, marker="o", label=skill)
+        else:
+            ax.plot(x_dt, y, label=skill)
+
+    ax.set_xlabel("Year-Month")
+    ax.set_ylabel(y_label if y_label.strip() else ("Normalized value" if normalize_mode!="none" else "Frequency"))
+    ax.set_title("Trend of Selected Hard Skills")
+    ax.legend(loc="best")
+    ax.grid(True, which="both", axis="both", alpha=0.35)
+
+    # Format x ticks with Month labels
+    ax.set_xticks(x_dt)
+    ax.set_xticklabels(x_labels, rotation=45, ha="right")
+
+    fig.tight_layout()
+    import io as _io
+    buf = _io.BytesIO()
+    fig.savefig(buf, format="png", dpi=160, bbox_inches="tight")
+    plt.close(fig)
+    buf.seek(0)
+    return buf  # return BytesIO; Gradio Image can accept bytes-like
+
+def run(
+    csv_file, selected_skills, smoothing_window, normalize_mode, show_markers, y_label
+):
+    df = load_dataframe(csv_file)
+    df = prepare_dataframe(df)
+    available = list_skill_columns(df)
+
+    # Auto-select if user didn't pick yet
+    if not selected_skills:
+        selected_skills = available
+
+    # Keep only existing skills
+    selected_skills = [s for s in selected_skills if s in available]
+
+    img_buf = plot_lines(df, selected_skills, smoothing_window, normalize_mode, show_markers, y_label)
+    # Also return a preview table for selected columns
+    preview_cols = ["YearMonth"] + selected_skills
+    preview = df[preview_cols].reset_index(drop=True)
+    return img_buf, gr.update(choices=available, value=selected_skills), preview
+
+with gr.Blocks(title="Hard Skills Trend Line Chart") as demo:
+    gr.Markdown("# Hard Skills Trend — Line Chart\nUpload a CSV or place **Trend_of_Top_10_Hard_Skills.csv** in the repo root.")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            csv_file = gr.File(label="Upload CSV (optional)", file_count="single", file_types=[".csv"])
+            selected_skills = gr.CheckboxGroup(choices=[], label="Select skills to plot")
+            smoothing_window = gr.Slider(1, 6, value=1, step=1, label="Smoothing (moving average window in months)")
+            normalize_mode = gr.Dropdown(choices=["none", "min-max (per skill)", "z-score (per skill)"], value="none", label="Normalize")
+            show_markers = gr.Checkbox(value=True, label="Show markers on lines")
+            y_label = gr.Textbox(value="", label="Y-axis label (optional)")
+            btn = gr.Button("Plot", variant="primary")
+
+        with gr.Column(scale=1):
+            out_img = gr.Image(label="Line Chart")
+            out_table = gr.Dataframe(label="Data preview")
+
+    # On click, return image, refresh skill choices, and table
+    btn.click(
+        fn=run,
+        inputs=[csv_file, selected_skills, smoothing_window, normalize_mode, show_markers, y_label],
+        outputs=[out_img, selected_skills, out_table]
+    )
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=4.26.0
+pandas>=2.0.0
+matplotlib>=3.8
+numpy