wizata-dsapi 2.0.0.dev21__tar.gz → 2.0.0.dev22__tar.gz

{wizata_dsapi-2.0.0.dev21/wizata_dsapi.egg-info → wizata_dsapi-2.0.0.dev22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wizata_dsapi
-Version: 2.0.0.dev21
+Version: 2.0.0.dev22
 Summary: Wizata Data Science Toolkit
 Author: Wizata S.A.
 Author-email: info@wizata.com

{wizata_dsapi-2.0.0.dev21 → wizata_dsapi-2.0.0.dev22}/wizata_dsapi/models/common.py

@@ -36,10 +36,7 @@ def extract_target_feat(context: wizata_dsapi.Context, single: bool = True):
 
 
 def linear_regression(context: wizata_dsapi.Context):
-    """
-    generic linear regression
-    - expects a valid single value target_feat
-    """
+    """Train a linear regression model on all features to predict a single target column."""
     df = context.dataframe
 
     model_config = context.get_model_config()
@@ -57,10 +54,7 @@ def linear_regression(context: wizata_dsapi.Context):
 
 
 def logistic_regression(context: wizata_dsapi.Context):
-    """
-    generic linear regression
-    - expects a valid single value target_feat
-    """
+    """Train a logistic regression classifier on all features to predict a binary target column."""
     df = context.dataframe
 
     model_config = context.get_model_config()
@@ -78,10 +72,7 @@ def logistic_regression(context: wizata_dsapi.Context):
 
 
 def isolation_forest(context: wizata_dsapi.Context):
-    """
-    isolation forest anomaly detection
-    - expects a no target feat model step
-    """
+    """Train an Isolation Forest for unsupervised anomaly detection using a sensitivity level (1-5)."""
 
     model_config = context.get_model_config()
     if model_config.has_target_feat():
@@ -104,11 +95,7 @@ def isolation_forest(context: wizata_dsapi.Context):
 
 
 def gradiant_boost_classifier(context: wizata_dsapi.Context):
-    """
-    gradiant_boost_classifier
-    :param context:
-    :return:
-    """
+    """Train a Gradient Boosting classifier on all features to predict a target column."""
     df = context.dataframe
 
     model_config = context.get_model_config()

wizata_dsapi-2.0.0.dev22/wizata_dsapi/plots/__init__.py

@@ -0,0 +1,2 @@
+from .common import ts_chart, confusion_matrix, r_squared, anomalies_chart, parallel_coordinates, data_table
+from . import theme

{wizata_dsapi-2.0.0.dev21 → wizata_dsapi-2.0.0.dev22}/wizata_dsapi/plots/common.py

@@ -6,6 +6,12 @@ import plotly.graph_objects as go
 import plotly.express as px
 import sklearn.metrics
 
+from .theme import (
+    apply_theme, SERIES_COLORS, ANOMALY_COLOR, TEXT_MUTED, WHITE,
+    TABLE_HEADER_BG, TABLE_HEADER_TEXT, TABLE_CELL_BG, TABLE_CELL_TEXT,
+    TABLE_LINE_COLOR, FONT_FAMILY, FONT_SIZE,
+)
+
 
 def check_single_column_and_target_feat(context: wizata_dsapi.Context):
     """
@@ -45,11 +51,7 @@ def check_single_column_and_target_feat(context: wizata_dsapi.Context):
 
 
 def confusion_matrix(context: wizata_dsapi.Context):
-    """
-    confusion_matrix
-    :param context:
-    :return:
-    """
+    """Plot a confusion matrix heatmap comparing predicted vs actual binary classes."""
     predict_df, ref_df = check_single_column_and_target_feat(context)
     cm = sklearn.metrics.confusion_matrix(ref_df, predict_df)
     inverted_cm = np.flip(cm, axis=1)
@@ -58,8 +60,8 @@ def confusion_matrix(context: wizata_dsapi.Context):
         z=inverted_cm,
         x=['Positive', 'Negative'],
         y=['Negative', 'Positive'],
-        colorscale='RdBu',
-        colorbar=dict(title='Count')
+        colorscale=[[0, '#062B56'], [1, '#E64600']],
+        colorbar=dict(title='Count', tickfont=dict(color=TEXT_MUTED)),
     ))
 
     for i in range(len(inverted_cm)):
@@ -69,7 +71,7 @@ def confusion_matrix(context: wizata_dsapi.Context):
                 y=i,
                 text=str(inverted_cm[i][j]),
                 showarrow=False,
-                font=dict(color='black' if inverted_cm[i][j] < np.max(inverted_cm) / 2 else 'white')
+                font=dict(color=WHITE if inverted_cm[i][j] > np.max(inverted_cm) / 2 else TEXT_MUTED)
             )
 
     fig.update_layout(
@@ -77,6 +79,8 @@ def confusion_matrix(context: wizata_dsapi.Context):
         yaxis=dict(title='Actual')
     )
 
+    apply_theme(fig)
+
     context.set_plot(
         figure=fig,
         name="confusion_matrix"
@@ -84,34 +88,41 @@ def confusion_matrix(context: wizata_dsapi.Context):
 
 
 def r_squared(context: wizata_dsapi.Context):
-    """
-    In statistics, the coefficient of determination, denoted R2 or r2 and pronounced "R squared", is the proportion of
-    the variation in the dependent variable that is predictable from the independent variable(s).
-    """
+    """Plot actual vs predicted scatter with R-squared coefficient and reference diagonal."""
     predict_df, ref_df = check_single_column_and_target_feat(context)
 
-    r_squared = sklearn.metrics.r2_score(ref_df, predict_df)
+    r2 = sklearn.metrics.r2_score(ref_df, predict_df)
 
     fig = go.Figure()
-    fig.add_trace(go.Scatter(x=ref_df.values.flatten(), y=predict_df.values.flatten(),
-                             mode='markers', name='Data Points'))
+    fig.add_trace(go.Scatter(
+        x=ref_df.values.flatten(),
+        y=predict_df.values.flatten(),
+        mode='markers',
+        name='Data Points',
+        marker=dict(color=SERIES_COLORS[0], size=5, opacity=0.7),
+    ))
 
     min_value = min(ref_df.values.min(), predict_df.values.min())
     max_value = max(ref_df.values.max(), predict_df.values.max())
-    fig.add_trace(go.Scatter(x=[min_value, max_value], y=[min_value, max_value],
-                             mode='lines', line=dict(color='black', dash='dash'), showlegend=False))
+    fig.add_trace(go.Scatter(
+        x=[min_value, max_value],
+        y=[min_value, max_value],
+        mode='lines',
+        line=dict(color=TEXT_MUTED, dash='dash'),
+        showlegend=False,
+    ))
 
     fig.add_annotation(
         x=min_value,
         y=max_value,
-        text=f'R^2 = {r_squared:.4f}',
+        text=f'R\u00b2 = {r2:.4f}',
         showarrow=False,
-        font=dict(color='black', size=12),
-        bgcolor='lightgrey',
-        bordercolor='black',
+        font=dict(color=WHITE, size=12),
+        bgcolor='#184980',
+        bordercolor='rgba(255,255,255,0.2)',
         borderwidth=1,
         borderpad=4,
-        opacity=0.8
+        opacity=0.9,
     )
 
     fig.update_layout(
@@ -119,6 +130,8 @@ def r_squared(context: wizata_dsapi.Context):
         yaxis=dict(title='Predicted')
     )
 
+    apply_theme(fig)
+
     context.set_plot(
         figure=fig,
         name="r_squared"
@@ -126,18 +139,22 @@ def r_squared(context: wizata_dsapi.Context):
 
 
 def ts_chart(context: wizata_dsapi.Context):
-    """
-    ts_chart
-    :param context:
-    :return:
-    """
+    """Plot all dataframe columns as time-series lines over the index."""
     df = context.dataframe
     traces = []
-    for column in df.columns:
-        trace = go.Scatter(x=df.index, y=df[column], mode='lines', name=column)
+    for i, column in enumerate(df.columns):
+        trace = go.Scatter(
+            x=df.index,
+            y=df[column],
+            mode='lines',
+            name=column,
+            line=dict(color=SERIES_COLORS[i % len(SERIES_COLORS)]),
+        )
         traces.append(trace)
 
     fig = go.Figure(traces)
+    apply_theme(fig)
+
     context.set_plot(
         figure=fig,
         name="ts_chart"
@@ -145,19 +162,23 @@ def ts_chart(context: wizata_dsapi.Context):
 
 
 def anomalies_chart(context: wizata_dsapi.Context):
-    """
-    anomalies_chart
-    :param context:
-    :return:
-    """
+    """Plot time-series signals with detected anomaly regions highlighted in red."""
     df = context.dataframe
 
     # Add Signals
     traces = []
+    color_idx = 0
     for column in df.columns:
         if column != "anomalies_type":
-            trace = go.Scatter(x=df.index, y=df[column], mode='lines', name=column)
+            trace = go.Scatter(
+                x=df.index,
+                y=df[column],
+                mode='lines',
+                name=column,
+                line=dict(color=SERIES_COLORS[color_idx % len(SERIES_COLORS)]),
+            )
             traces.append(trace)
+            color_idx += 1
     fig = go.Figure(traces)
 
     # Add Anomalies as Highlighted
@@ -173,7 +194,9 @@ def anomalies_chart(context: wizata_dsapi.Context):
     anomalies_occurrences.columns = ['from', 'to', 'anomaly_group']
     for i in anomalies_occurrences.index:
         fig.add_vrect(x0=anomalies_occurrences['from'][i], x1=anomalies_occurrences['to'][i], line_width=0,
-                      fillcolor="red", opacity=0.2)
+                      fillcolor=ANOMALY_COLOR, opacity=1)
+
+    apply_theme(fig)
 
     context.set_plot(
         figure=fig,
@@ -182,19 +205,66 @@ def anomalies_chart(context: wizata_dsapi.Context):
 
 
 def parallel_coordinates(context: wizata_dsapi.Context):
-    """
-    parallel_coordinates
-    :param context:
-    :return:
-    """
+    """Plot parallel coordinates colored by anomaly type for multi-dimensional analysis."""
     df = context.dataframe
 
     fig = px.parallel_coordinates(df,
                                   color='anomalies_type',
                                   dimensions=df,
                                   color_continuous_scale=px.colors.diverging.Portland)
+    apply_theme(fig)
+
     context.set_plot(
         figure=fig,
         name="parallel_coordinates"
     )
 
+
+def data_table(context: wizata_dsapi.Context):
+    """Render the dataframe as a styled table with Wizata theme colors."""
+    df = context.dataframe.copy()
+
+    # Format the index as a column if it has a name or is a DatetimeIndex
+    if isinstance(df.index, pd.DatetimeIndex):
+        df.insert(0, df.index.name or "Timestamp", df.index.strftime("%Y-%m-%d %H:%M:%S"))
+        df = df.reset_index(drop=True)
+    elif df.index.name is not None:
+        df = df.reset_index()
+
+    # Round numeric columns
+    precision = int(context.properties.get("precision", 4)) if "precision" in context.properties else 4
+    for col in df.select_dtypes(include="number").columns:
+        df[col] = df[col].round(precision)
+
+    # Build alternating row colors
+    n_rows = len(df)
+    cell_bg = [TABLE_CELL_BG[i % 2] for i in range(n_rows)]
+
+    fig = go.Figure(data=[go.Table(
+        header=dict(
+            values=[f"<b>{c}</b>" for c in df.columns],
+            fill_color=TABLE_HEADER_BG,
+            font=dict(family=FONT_FAMILY, size=FONT_SIZE, color=TABLE_HEADER_TEXT),
+            align="left",
+            line_color=TABLE_LINE_COLOR,
+            height=32,
+        ),
+        cells=dict(
+            values=[df[c].tolist() for c in df.columns],
+            fill_color=[cell_bg],
+            font=dict(family=FONT_FAMILY, size=FONT_SIZE, color=TABLE_CELL_TEXT),
+            align="left",
+            line_color=TABLE_LINE_COLOR,
+            height=28,
+        ),
+    )])
+
+    fig.update_layout(
+        margin=dict(l=0, r=0, t=0, b=0),
+    )
+    apply_theme(fig)
+
+    context.set_plot(
+        figure=fig,
+        name="data_table"
+    )

wizata_dsapi-2.0.0.dev22/wizata_dsapi/plots/theme.py

@@ -0,0 +1,104 @@
+"""
+Wizata chart theme for Plotly figures.
+
+Provides consistent colors, fonts, and layout defaults
+designed for rendering on the Wizata platform dark background.
+"""
+
+# -- Brand --------------------------------------------------------------------
+MAIN_COLOR = "#E64600"
+
+# Blue shades
+SECONDARY = "#184980"
+TERTIARY = "#031E37"
+FOURTH = "#062B56"
+
+WHITE = "#FFFFFF"
+TEXT_MUTED = "#B8C4D0"
+BACKGROUND = "#01101D"
+
+# -- Status -------------------------------------------------------------------
+STATUS_SUCCESS = "#7CFFB2"
+STATUS_WARNING = "#FDDD60"
+STATUS_ERROR = "#FF6E76"
+STATUS_INFO = "#4992FF"
+STATUS_ABORTED = "#9B9BA2"
+
+# -- Data series (ordered cycle) ----------------------------------------------
+SERIES_COLORS = [
+    "#7CFFB2",
+    "#9E7CFF",
+    "#FDDD60",
+    "#4992FF",
+    "#6FE7F7",
+    "#E992FF",
+    "#FF6E76",
+    "#FFA686",
+    "#D1E2EE",
+    "#FFF0B5",
+    "#91C778",
+    "#7B7D88",
+]
+
+# -- Semantic -----------------------------------------------------------------
+ANOMALY_COLOR = "rgba(255,110,118,0.25)"  # STATUS_ERROR at 25%
+POSITIVE_COLOR = STATUS_SUCCESS
+NEGATIVE_COLOR = STATUS_ERROR
+NEUTRAL_COLOR = STATUS_INFO
+
+# -- Table --------------------------------------------------------------------
+TABLE_HEADER_BG = SECONDARY
+TABLE_HEADER_TEXT = WHITE
+TABLE_CELL_BG = [TERTIARY, FOURTH]
+TABLE_CELL_TEXT = TEXT_MUTED
+TABLE_LINE_COLOR = "rgba(255,255,255,0.12)"
+
+# -- Font ---------------------------------------------------------------------
+FONT_FAMILY = "Inter, -apple-system, BlinkMacSystemFont, sans-serif"
+FONT_SIZE = 12
+TITLE_SIZE = 14
+
+# -- Layout defaults ----------------------------------------------------------
+TRANSPARENT = "rgba(0,0,0,0)"
+
+LAYOUT_DEFAULTS = dict(
+    paper_bgcolor=TRANSPARENT,
+    plot_bgcolor=TRANSPARENT,
+    font=dict(
+        family=FONT_FAMILY,
+        size=FONT_SIZE,
+        color=TEXT_MUTED,
+    ),
+    title=dict(
+        font=dict(size=TITLE_SIZE, color=WHITE),
+    ),
+    legend=dict(
+        bgcolor=TRANSPARENT,
+        font=dict(color=TEXT_MUTED),
+    ),
+    xaxis=dict(
+        gridcolor="rgba(255,255,255,0.08)",
+        linecolor="rgba(255,255,255,0.2)",
+        zerolinecolor="rgba(255,255,255,0.08)",
+        tickfont=dict(color=TEXT_MUTED),
+        title_font=dict(color=TEXT_MUTED),
+    ),
+    yaxis=dict(
+        gridcolor="rgba(255,255,255,0.08)",
+        linecolor="rgba(255,255,255,0.2)",
+        zerolinecolor="rgba(255,255,255,0.08)",
+        tickfont=dict(color=TEXT_MUTED),
+        title_font=dict(color=TEXT_MUTED),
+    ),
+    colorway=SERIES_COLORS,
+    margin=dict(l=50, r=20, t=40, b=40),
+)
+
+
+def apply_theme(fig):
+    """
+    Apply Wizata theme to an existing Plotly figure.
+    Returns the figure for chaining.
+    """
+    fig.update_layout(**LAYOUT_DEFAULTS)
+    return fig

{wizata_dsapi-2.0.0.dev21 → wizata_dsapi-2.0.0.dev22}/wizata_dsapi/scripts/common.py

@@ -10,11 +10,7 @@ import sklearn.ensemble
 
 
 def filter_df(context: wizata_dsapi.Context):
-    """
-    filter a dataframe
-    :param context:
-    :return:
-    """
+    """Filter dataframe rows using pandas query strings from the 'filters' property list."""
 
     if "filters" not in context.properties or not isinstance(context.properties['filters'], list):
         raise ValueError(f'there is no list *filters* in properties - please set them on context or config')
@@ -32,11 +28,7 @@ def filter_df(context: wizata_dsapi.Context):
 
 
 def clustering(context: wizata_dsapi.Context):
-    """
-    clustering
-    :param context:
-    :return:
-    """
+    """K-means clustering with automatic cluster count selection via silhouette score."""
     df = context.dataframe.copy()
     scaler = sklearn.preprocessing.StandardScaler()
     df_clustering_scaler = scaler.fit_transform(df)
@@ -68,11 +60,7 @@ def clustering(context: wizata_dsapi.Context):
 
 
 def merge(context: wizata_dsapi.Context):
-    """
-    merge
-    :param context:
-    :return:
-    """
+    """Merge multiple dataframes by index using outer join (configurable via 'how' property)."""
     dataframes = context.current_dataframes()
     if len(dataframes) <= 1:
         raise ValueError(f'there is not enough dataframes to concat')
@@ -91,11 +79,7 @@ def merge(context: wizata_dsapi.Context):
 
 
 def fillna(context: wizata_dsapi.Context):
-    """
-    fillna
-    :param context:
-    :return:
-    """
+    """Fill missing values per column using the 'fillna' property dict mapping column names to fill values."""
     df = context.dataframe
 
     if "fillna" not in context.properties:
@@ -108,11 +92,7 @@ def fillna(context: wizata_dsapi.Context):
 
 
 def target_feat_to_binary(context: wizata_dsapi.Context):
-    """
-    target_feat_to_binary
-    :param context:
-    :return:
-    """
+    """Convert a target feature column to binary (0/1) using a threshold operator (lt, lte, gt, gte)."""
     df = context.dataframe
 
     if "target_feat" not in context.properties:

wizata_dsapi-2.0.0.dev22/wizata_dsapi/version.py

@@ -0,0 +1 @@
+__version__ = "2.0.0.dev22"

{wizata_dsapi-2.0.0.dev21 → wizata_dsapi-2.0.0.dev22/wizata_dsapi.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wizata_dsapi
-Version: 2.0.0.dev21
+Version: 2.0.0.dev22
 Summary: Wizata Data Science Toolkit
 Author: Wizata S.A.
 Author-email: info@wizata.com

{wizata_dsapi-2.0.0.dev21 → wizata_dsapi-2.0.0.dev22}/wizata_dsapi.egg-info/SOURCES.txt

@@ -58,5 +58,6 @@ wizata_dsapi/models/__init__.py
 wizata_dsapi/models/common.py
 wizata_dsapi/plots/__init__.py
 wizata_dsapi/plots/common.py
+wizata_dsapi/plots/theme.py
 wizata_dsapi/scripts/__init__.py
 wizata_dsapi/scripts/common.py

wizata_dsapi-2.0.0.dev21/wizata_dsapi/plots/__init__.py

@@ -1 +0,0 @@
-from .common import ts_chart, confusion_matrix, r_squared, anomalies_chart, parallel_coordinates

wizata_dsapi-2.0.0.dev21/wizata_dsapi/version.py

@@ -1 +0,0 @@
-__version__ = "2.0.0.dev21"