Update charts.py

charts.py

@@ -1,28 +1,21 @@
-"""
-charts.py — All Plotly chart builders. Pure functions, no Streamlit imports.
-"""
-
 from typing import Dict, List, Tuple, Optional
 import plotly.graph_objects as go
 import plotly.express as px
 import pandas as pd
 import numpy as np
 
-#  Shared theme — Stormy Morning & Ink Wash palette
-DARK_BG     = "#FFFFE3"          # Ink Wash Cream — used as bar marker-line for "floating" effect
-CARD_BG     = "#FFFFFF"          # white card base
-BORDER      = "#BDDDFC"          # Stormy Light
-TEXT_MAIN   = "#4A4A4A"          # Ink Wash Dark
-TEXT_DIM    = "#7b7b7b"          # muted text
-PRIMARY     = "#269ccc"          # Optimism Blue
-CYAN        = "#269ccc"          # alias for PRIMARY
-
-# Sentiment palette — Stormy Morning
-POS_COLOR   = "#88BDF2"          # Stormy Sky       — Positively Engagement
-NEG_COLOR   = "#6A89A7"          # Stormy Slate     — Negatively Engagement
-NEU_COLOR   = "#CBCBCB"          # Ink Wash Grey    — Neutral
-
-# Legacy / other chart colours
+DARK_BG     = "#FFFFE3"
+CARD_BG     = "#FFFFFF"
+BORDER      = "#BDDDFC"
+TEXT_MAIN   = "#2d2d2d"
+TEXT_DIM    = "#555555"
+PRIMARY     = "#269ccc"
+CYAN        = "#269ccc"
+
+POS_COLOR   = "#88BDF2"
+NEG_COLOR   = "#6A89A7"
+NEU_COLOR   = "#CBCBCB"
+
 ALGAE       = "#9ed2c5"
 GREEN       = "#16a34a"
 RED         = "#dc2626"
@@ -30,18 +23,20 @@ AMBER       = "#d97706"
 PURPLE      = "#7c3aed"
 BLUE        = "#2563eb"
 
+_FONT       = dict(family="'DM Sans', 'Nunito', sans-serif", color=TEXT_MAIN, size=12)
+_TITLE_FONT = dict(family="'DM Sans', sans-serif", color=TEXT_MAIN, size=13)
+_TICK_FONT  = dict(family="'DM Sans', sans-serif", color=TEXT_MAIN, size=11)
+_LEGEND_FONT= dict(family="'DM Sans', sans-serif", color=TEXT_MAIN, size=11)
+
 PLOTLY_LAYOUT = dict(
-    paper_bgcolor="rgba(255,255,227,0)",   # transparent over cream bg
-    plot_bgcolor="rgba(255,255,227,0)",    # transparent — card provides bg
-    font=dict(family="'DM Sans', 'Nunito', sans-serif", color=TEXT_MAIN, size=12),
-    margin=dict(l=20, r=20, t=40, b=20),
+    paper_bgcolor="rgba(255,255,227,0)",
+    plot_bgcolor="rgba(189,221,252,0.13)",
+    font=_FONT,
+    margin=dict(l=20, r=20, t=44, b=20),
 )
 
 
-#  Misinformation Gauge 
-
 def misinfo_gauge(score: float, label: str) -> go.Figure:
-    """Gauge chart for misinformation confidence score (0–1)."""
     pct = score * 100
     if score < 0.35:
         bar_color = GREEN
@@ -55,13 +50,13 @@ def misinfo_gauge(score: float, label: str) -> go.Figure:
         value=pct,
         number={"suffix": "%", "font": {"size": 32, "color": bar_color, "family": "'Nunito', sans-serif"}},
         delta={"reference": 50, "increasing": {"color": RED}, "decreasing": {"color": GREEN}},
-        title={"text": label, "font": {"size": 13, "color": TEXT_DIM}},
+        title={"text": label, "font": {"size": 13, "color": TEXT_MAIN}},
         gauge={
             "axis": {
                 "range": [0, 100],
                 "tickwidth": 1,
                 "tickcolor": BORDER,
-                "tickfont": {"color": TEXT_DIM, "size": 10},
+                "tickfont": {"color": TEXT_MAIN, "size": 10},
             },
             "bar": {"color": bar_color, "thickness": 0.3},
             "bgcolor": CARD_BG,
@@ -82,10 +77,7 @@ def misinfo_gauge(score: float, label: str) -> go.Figure:
     return fig
 
 
-#  Sentiment Donut ─
-
 def sentiment_donut(summary: Dict) -> go.Figure:
-    """Donut chart: Positively Engagement / Negatively Engagement / Neutral breakdown."""
     labels  = ["Positively Engagement", "Neutral", "Negatively Engagement"]
     values  = [summary["Positively Engagement"], summary["Neutral"], summary["Negatively Engagement"]]
     colors  = [POS_COLOR, NEU_COLOR, NEG_COLOR]
@@ -101,7 +93,6 @@ def sentiment_donut(summary: Dict) -> go.Figure:
         rotation=90,
     ))
 
-    # Centre annotation
     avg = summary.get("avg_compound", 0)
     overall = "😊 Positively Engaged" if avg > 0.05 else ("😟 Negatively Engaged" if avg < -0.05 else "😐 Mixed")
     fig.add_annotation(
@@ -111,14 +102,15 @@ def sentiment_donut(summary: Dict) -> go.Figure:
         font=dict(size=13, color=TEXT_MAIN, family="'DM Sans', sans-serif"),
         align="center",
     )
-    fig.update_layout(**PLOTLY_LAYOUT, height=300,
-                      legend=dict(orientation="h", y=-0.08, font=dict(size=11)),
-                      title=dict(text="Sentiment Breakdown", font=dict(size=13, color=TEXT_DIM), x=0))
+    fig.update_layout(
+        **PLOTLY_LAYOUT,
+        height=300,
+        legend=dict(orientation="h", y=-0.08, font=_LEGEND_FONT),
+        title=dict(text="Sentiment Breakdown", font=_TITLE_FONT, x=0),
+    )
     return fig
 
 
-#  Keyword Bar Chart ─
-
 def keyword_bar(
     keywords: List[Tuple[str, float]],
     title: str = "Top Keywords",
@@ -128,7 +120,6 @@ def keyword_bar(
         return _empty_fig(title)
 
     words, weights = zip(*keywords[:15])
-    # Normalize to 0-100
     max_w = max(weights) or 1
     norm = [w / max_w * 100 for w in weights]
 
@@ -139,7 +130,7 @@ def keyword_bar(
         marker=dict(
             color=norm,
             colorscale=[[0, f"{PRIMARY}33"], [1, PRIMARY]],
-            line=dict(color=DARK_BG, width=1.5),  # floating effect — matches bg
+            line=dict(color=DARK_BG, width=1.5),
         ),
         text=[f"{w:.0f}" for w in weights],
         textposition="inside",
@@ -148,21 +139,28 @@ def keyword_bar(
     ))
     fig.update_layout(
         **PLOTLY_LAYOUT,
-        title=dict(text=title, font=dict(size=13, color=TEXT_DIM), x=0),
+        title=dict(text=title, font=_TITLE_FONT, x=0),
         height=380,
-        yaxis=dict(autorange="reversed", tickfont=dict(size=11), gridcolor=BORDER,
-                   showgrid=True, gridwidth=1),
-        xaxis=dict(showticklabels=False, gridcolor=BORDER, showgrid=False),
+        yaxis=dict(
+            autorange="reversed",
+            tickfont=_TICK_FONT,
+            title_font=_TITLE_FONT,
+            gridcolor=BORDER,
+            showgrid=True,
+            gridwidth=1,
+        ),
+        xaxis=dict(
+            showticklabels=False,
+            gridcolor=BORDER,
+            showgrid=False,
+        ),
         bargap=0.3,
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Stream Trust Bars ─
-
 def stream_trust_bars(stream_details: Dict) -> go.Figure:
-    """Horizontal bar chart for per-stream misinfo scores."""
     labels = list(stream_details.keys())
     values = [round(v * 100, 1) for v in stream_details.values()]
     colors = [RED if v > 50 else (AMBER if v > 30 else GREEN) for v in values]
@@ -179,33 +177,16 @@ def stream_trust_bars(stream_details: Dict) -> go.Figure:
     ))
     fig.update_layout(
         **PLOTLY_LAYOUT,
-        title=dict(text="Per-Stream Analysis", font=dict(size=13, color=TEXT_DIM), x=0),
+        title=dict(text="Per-Stream Analysis", font=_TITLE_FONT, x=0),
         height=220,
-        xaxis=dict(range=[0, 110], showticklabels=False, gridcolor=BORDER),
-        yaxis=dict(tickfont=dict(size=11)),
+        xaxis=dict(range=[0, 110], showticklabels=False, gridcolor=BORDER, tickfont=_TICK_FONT),
+        yaxis=dict(tickfont=_TICK_FONT),
         bargap=0.4,
     )
     return fig
 
 
-#  Modality Misinformation Distribution ─
-
 def modality_misinfo_distribution(modality_analysis: Dict) -> go.Figure:
-    """
-    Grouped bar chart — Misinformation Score vs Not-Misinformation Score per modality.
-
-    Bars are derived directly from the model's per-stream softmax probabilities
-    (values in ``modality_analysis[modality]["misinfo_pct"]`` /
-    ``modality_analysis[modality]["credible_pct"]``).
-    Each pair of bars sums to exactly 100 % because they are complementary
-    softmax outputs from the same binary classification head.
-
-    Parameters
-    ----------
-    modality_analysis : dict
-        Mapping  {"text": {...}, "audio": {...}, "video": {...}}  as returned by
-        ``analyzer._compute_modality_analysis()`` — one sub-dict per stream.
-    """
     MODALITIES = ["Text", "Audio", "Video"]
     KEYS       = ["text", "audio", "video"]
 
@@ -226,7 +207,7 @@ def modality_misinfo_distribution(modality_analysis: Dict) -> go.Figure:
         marker=dict(
             color=[RED, RED, RED],
             opacity=0.88,
-            line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+            line=dict(color=DARK_BG, width=1.5),
         ),
         text=[f"{v:.1f}%" for v in misinfo_pcts],
         textposition="outside",
@@ -246,7 +227,7 @@ def modality_misinfo_distribution(modality_analysis: Dict) -> go.Figure:
         marker=dict(
             color=[GREEN, GREEN, GREEN],
             opacity=0.88,
-            line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+            line=dict(color=DARK_BG, width=1.5),
         ),
         text=[f"{v:.1f}%" for v in credible_pcts],
         textposition="outside",
@@ -263,18 +244,21 @@ def modality_misinfo_distribution(modality_analysis: Dict) -> go.Figure:
         **PLOTLY_LAYOUT,
         title=dict(
             text="Modality Misinformation Distribution",
-            font=dict(size=13, color=TEXT_DIM),
+            font=_TITLE_FONT,
             x=0,
         ),
         barmode="group",
         height=280,
         xaxis=dict(
             title="Modality",
-            tickfont=dict(size=12),
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             gridcolor=BORDER,
         ),
         yaxis=dict(
             title="Softmax Score (%)",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             range=[0, 115],
             gridcolor=BORDER,
             ticksuffix="%",
@@ -282,30 +266,17 @@ def modality_misinfo_distribution(modality_analysis: Dict) -> go.Figure:
         legend=dict(
             orientation="h",
             y=1.12,
-            font=dict(size=11),
+            font=_LEGEND_FONT,
             bgcolor="rgba(255,255,227,0)",
         ),
         bargap=0.22,
         bargroupgap=0.06,
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Trust Score by Modality ─
-
 def trust_score_by_modality(modality_analysis: Dict) -> go.Figure:
-    """
-    Vertical bar chart — model's reliability/trustworthiness coefficient per stream.
-
-    Trust is computed as a linear combination of model confidence (1 – Shannon entropy)
-    and content-richness, both derived from the actual inference pass, never fixed.
-
-    Parameters
-    ----------
-    modality_analysis : dict
-        Same structure as ``modality_misinfo_distribution``.
-    """
     MODALITIES = ["Text", "Audio", "Video"]
     KEYS       = ["text", "audio", "video"]
 
@@ -321,7 +292,7 @@ def trust_score_by_modality(modality_analysis: Dict) -> go.Figure:
         marker=dict(
             color=bar_colors,
             opacity=0.88,
-            line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+            line=dict(color=DARK_BG, width=1.5),
         ),
         text=[f"{v:.1f}%" for v in trust_vals],
         textposition="outside",
@@ -334,7 +305,6 @@ def trust_score_by_modality(modality_analysis: Dict) -> go.Figure:
         ),
     ))
 
-    # Reference lines
     for level, label, color in [(80, "High Trust", GREEN), (50, "Threshold", AMBER)]:
         fig.add_hline(
             y=level,
@@ -348,49 +318,37 @@ def trust_score_by_modality(modality_analysis: Dict) -> go.Figure:
         **PLOTLY_LAYOUT,
         title=dict(
             text="Trust Score by Modality",
-            font=dict(size=13, color=TEXT_DIM),
+            font=_TITLE_FONT,
             x=0,
         ),
         height=280,
         xaxis=dict(
             title="Modality",
-            tickfont=dict(size=12),
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             gridcolor=BORDER,
         ),
         yaxis=dict(
             title="Trust Level (%)",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             range=[0, 115],
             gridcolor=BORDER,
             ticksuffix="%",
         ),
         bargap=0.38,
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Uncertainty Analysis 
-
 def uncertainty_analysis(modality_analysis: Dict) -> go.Figure:
-    """
-    Vertical bar chart — Shannon entropy of the model's softmax distribution per stream.
-
-    High entropy ( → 100 %) means the model is maximally unsure (uniform distribution).
-    Low entropy ( → 0 %) means the model is highly confident in its prediction.
-    Values come directly from H = –Σ p·log₂(p) over the two softmax outputs.
-
-    Parameters
-    ----------
-    modality_analysis : dict
-        Same structure as ``modality_misinfo_distribution``.
-    """
     MODALITIES = ["Text", "Audio", "Video"]
     KEYS       = ["text", "audio", "video"]
 
     uncertainty_vals = [modality_analysis.get(k, {}).get("uncertainty", 100.0) for k in KEYS]
     misinfo_pcts     = [modality_analysis.get(k, {}).get("misinfo_pct", 50.0)  for k in KEYS]
 
-    # Colour encodes confidence direction: red = uncertain, green = confident
     bar_colors = [
         (GREEN if v <= 35 else (AMBER if v <= 65 else RED))
         for v in uncertainty_vals
@@ -402,7 +360,7 @@ def uncertainty_analysis(modality_analysis: Dict) -> go.Figure:
         marker=dict(
             color=bar_colors,
             opacity=0.88,
-            line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+            line=dict(color=DARK_BG, width=1.5),
         ),
         text=[f"{v:.1f}%" for v in uncertainty_vals],
         textposition="outside",
@@ -417,7 +375,6 @@ def uncertainty_analysis(modality_analysis: Dict) -> go.Figure:
         ),
     ))
 
-    # Max-entropy reference
     fig.add_hline(
         y=100,
         line=dict(color=RED, width=1, dash="dot"),
@@ -437,31 +394,31 @@ def uncertainty_analysis(modality_analysis: Dict) -> go.Figure:
         **PLOTLY_LAYOUT,
         title=dict(
             text="Uncertainty Analysis (Shannon Entropy)",
-            font=dict(size=13, color=TEXT_DIM),
+            font=_TITLE_FONT,
             x=0,
         ),
         height=280,
         xaxis=dict(
             title="Modality",
-            tickfont=dict(size=12),
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             gridcolor=BORDER,
         ),
         yaxis=dict(
             title="Uncertainty (%)",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
             range=[0, 120],
             gridcolor=BORDER,
             ticksuffix="%",
         ),
         bargap=0.38,
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Comment Sentiment Timeline 
-
 def sentiment_timeline(comments_df: pd.DataFrame, sentiments: List[Dict]) -> go.Figure:
-    """Scatter: comment likes vs. sentiment compound score."""
     if comments_df.empty:
         return _empty_fig("Comment Sentiment Distribution")
 
@@ -502,25 +459,41 @@ def sentiment_timeline(comments_df: pd.DataFrame, sentiments: List[Dict]) -> go.
     fig.add_hline(y=0, line=dict(color=BORDER, width=1, dash="dot"))
     fig.update_layout(
         **PLOTLY_LAYOUT,
-        title=dict(text="Comment Sentiment (size = likes)", font=dict(size=13, color=TEXT_DIM), x=0),
+        title=dict(text="Comment Sentiment (size = likes)", font=_TITLE_FONT, x=0),
         height=320,
-        xaxis=dict(title="Comment index", gridcolor=BORDER, showgrid=False),
-        yaxis=dict(title="Compound score", gridcolor=BORDER, range=[-1.1, 1.1],
-                   showgrid=True, gridwidth=1),
-        legend=dict(orientation="h", y=1.12, font=dict(size=11),
-                    bgcolor="rgba(255,255,227,0.8)", bordercolor=BORDER, borderwidth=1),
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        xaxis=dict(
+            title="Comment index",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
+            gridcolor=BORDER,
+            showgrid=False,
+        ),
+        yaxis=dict(
+            title="Compound score",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
+            gridcolor=BORDER,
+            range=[-1.1, 1.1],
+            showgrid=True,
+            gridwidth=1,
+        ),
+        legend=dict(
+            orientation="h",
+            y=1.12,
+            font=_LEGEND_FONT,
+            bgcolor="rgba(255,255,255,0.85)",
+            bordercolor=BORDER,
+            borderwidth=1,
+        ),
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Positively Engagement vs Negatively Engagement Keyword Comparison ─
-
 def keyword_comparison(
     pos_kw: List[Tuple[str, float]],
     neg_kw: List[Tuple[str, float]],
 ) -> go.Figure:
-    """Diverging bar chart: Positive keywords right, negative left."""
     if not pos_kw and not neg_kw:
         return _empty_fig("Sentiment Keywords")
 
@@ -540,11 +513,11 @@ def keyword_comparison(
             orientation="h",
             marker=dict(
                 color=POS_COLOR,
-                line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+                line=dict(color=DARK_BG, width=1.5),
             ),
             text=[f"{v/max_p*100:.0f}" for v in pv],
             textposition="outside",
-            textfont=dict(size=10, color=TEXT_DIM),
+            textfont=dict(size=10, color=TEXT_MAIN),
             hovertemplate="<b>%{y}</b><br>Score: %{x:.1f}<extra></extra>",
         ))
 
@@ -558,35 +531,54 @@ def keyword_comparison(
             orientation="h",
             marker=dict(
                 color=NEG_COLOR,
-                line=dict(color=DARK_BG, width=1.5),  # floating bar lines
+                line=dict(color=DARK_BG, width=1.5),
             ),
             text=[f"{v/max_n*100:.0f}" for v in nv],
             textposition="outside",
-            textfont=dict(size=10, color=TEXT_DIM),
+            textfont=dict(size=10, color=TEXT_MAIN),
             hovertemplate="<b>%{y}</b><br>Score: %{x:.1f}<extra></extra>",
         ))
 
     fig.update_layout(
         **PLOTLY_LAYOUT,
-        title=dict(text="Sentiment-Weighted Keywords", font=dict(size=13, color=TEXT_DIM), x=0),
+        title=dict(text="Sentiment-Weighted Keywords", font=_TITLE_FONT, x=0),
         height=360,
         barmode="overlay",
-        xaxis=dict(title="← Negatively Engagement  |  Positively Engagement →", gridcolor=BORDER,
-                   zeroline=True, zerolinecolor=BORDER, zerolinewidth=2),
-        yaxis=dict(tickfont=dict(size=10)),
-        legend=dict(orientation="h", y=1.1, bgcolor="rgba(255,255,227,0.8)",
-                    bordercolor=BORDER, borderwidth=1),
-        plot_bgcolor="rgba(189,221,252,0.08)",
+        xaxis=dict(
+            title="← Negatively Engagement  |  Positively Engagement →",
+            title_font=_TITLE_FONT,
+            tickfont=_TICK_FONT,
+            gridcolor=BORDER,
+            zeroline=True,
+            zerolinecolor=BORDER,
+            zerolinewidth=2,
+        ),
+        yaxis=dict(tickfont=_TICK_FONT),
+        legend=dict(
+            orientation="h",
+            y=1.1,
+            font=_LEGEND_FONT,
+            bgcolor="rgba(255,255,255,0.85)",
+            bordercolor=BORDER,
+            borderwidth=1,
+        ),
+        plot_bgcolor="rgba(189,221,252,0.13)",
     )
     return fig
 
 
-#  Helpers ─
-
 def _empty_fig(title: str) -> go.Figure:
     fig = go.Figure()
-    fig.add_annotation(text="No data available", x=0.5, y=0.5, showarrow=False,
-                       font=dict(size=14, color=TEXT_DIM))
-    fig.update_layout(**PLOTLY_LAYOUT, title=dict(text=title, x=0), height=250,
-                      plot_bgcolor="rgba(189,221,252,0.08)")
+    fig.add_annotation(
+        text="No data available",
+        x=0.5, y=0.5,
+        showarrow=False,
+        font=dict(size=14, color=TEXT_MAIN),
+    )
+    fig.update_layout(
+        **PLOTLY_LAYOUT,
+        title=dict(text=title, font=_TITLE_FONT, x=0),
+        height=250,
+        plot_bgcolor="rgba(189,221,252,0.13)",
+    )
     return fig