direl-ts-tool-kit 0.4.9__py3-none-any.whl → 0.6.0__py3-none-any.whl

direl_ts_tool_kit/plot/plot_style.py

@@ -1,5 +1,8 @@
+import seaborn as sns
 import matplotlib.pyplot as plt
 import matplotlib.dates as mdates
+from matplotlib.lines import Line2D
+
 
 plt.style.use("fast")
 

direl_ts_tool_kit/plot/plot_ts.py

@@ -1,8 +1,17 @@
+import numpy as np
+import pandas as pd
 from .plot_style import *
+from scipy.stats import pearsonr
 
 
 def plot_time_series(
-    df_ts, variable, units="", color="BLUE_LINES", time_unit="Year", rot=90, auto_format_label=True
+    df_ts,
+    variable,
+    units="",
+    color="BLUE_LINES",
+    time_unit="Year",
+    rot=90,
+    auto_format_label=True,
 ):
     """
     Plots a time series with custom styling and dual-level grid visibility.
@@ -100,7 +109,7 @@ def plot_time_series(
     if time_unit == "Day":
         ax.xaxis.set_major_locator(mdates.DayLocator())
         ax.xaxis.set_minor_locator(mdates.HourLocator())
-        
+
     if time_unit == "Hour":
         ax.xaxis.set_major_locator(mdates.HourLocator())
         ax.xaxis.set_minor_locator(mdates.MinuteLocator())
@@ -113,6 +122,159 @@ def plot_time_series(
     return fig
 
 
+def plot_interpolation_analysis(
+    df_original,
+    variable,
+    units="",
+    method="polynomial",
+    order=2,
+    imputation_se=None,
+    time_unit="Year",
+    rot=90,
+):
+    """
+    Performs interpolation on missing data (NaNs) in a specified column and
+    plots the result, highlighting the imputed points with confidence intervals
+    if the Imputation Standard Error (SE) is provided.
+
+    Parameters
+    ----------
+    df_original : pd.DataFrame
+        The DataFrame containing the original time series data.
+    variable : str
+        The name of the column to interpolate and plot (e.g., 'LPUE').
+    units : str, optional
+        Units to display next to the variable name on the y-axis. Defaults to "".
+    method : str, optional
+        The interpolation method (e.g., 'linear', 'polynomial', 'spline').
+        Defaults to 'polynomial'.
+    order : int, optional
+        The order of the interpolation (required for 'polynomial' or 'spline').
+        Defaults to 2.
+    imputation_se : pd.Series, float, or None, optional
+        The Standard Error (SE) of the imputation. This must be a single value
+        or a Series aligned with the DataFrame's index. If None, confidence
+        intervals will NOT be plotted. Defaults to None.
+    time_unit : str, optional
+        The time granularity for x-axis tick locators. Defaults to "Year".
+    rot : int, optional
+        Rotation angle (in degrees) for the x-axis tick labels. Defaults to 90.
+
+    Returns
+    -------
+    matplotlib.figure.Figure
+        The generated Matplotlib figure object with the plot.
+    """
+
+    imputed_mask = df_original[variable].isnull()
+    df_interpolated = df_original.copy()
+    df_interpolated[variable] = df_interpolated[variable].interpolate(
+        method=method, order=order
+    )
+
+    color1 = paper_colors["RED_LINES"]
+    color2 = paper_colors["GREEN_LINES"]
+
+    col = np.where(imputed_mask, color1, color2)
+
+    fig, ax = plt.subplots()
+
+    if imputation_se is not None:
+        df_imputed_only = df_interpolated.copy()
+        df_imputed_only.loc[~imputed_mask, variable] = np.nan
+
+        Z_80 = 1.282
+        Z_95 = 1.96
+
+        error_80 = Z_80 * imputation_se
+        error_95 = Z_95 * imputation_se
+
+        ax.fill_between(
+            df_imputed_only.index,
+            df_imputed_only[variable] - error_95,
+            df_imputed_only[variable] + error_95,
+            color=paper_colors["GRAY_BARS"],
+            alpha=0.2,
+            edgecolor="none",
+            label="95% confidence interval",
+        )
+
+        ax.fill_between(
+            df_imputed_only.index,
+            df_imputed_only[variable] - error_80,
+            df_imputed_only[variable] + error_80,
+            color=paper_colors["GRAY_BARS"],
+            alpha=0.4,
+            edgecolor="none",
+            label="80% confidence interval",
+        )
+
+    ax.plot(
+        df_interpolated[variable],
+        linestyle="-.",
+        linewidth=1,
+        color=paper_colors["BLUE_LINES"],
+    )
+
+    ax.scatter(
+        df_interpolated.index,
+        df_interpolated[variable],
+        color=col,
+        s=10,
+        linewidth=4,
+    )
+
+    ax.set(xlabel=f"{time_unit}", ylabel=f"{variable} {units}")
+    ax.ticklabel_format(style="sci", axis="y", scilimits=(0, 0))
+
+    if time_unit == "Year":
+        ax.xaxis.set_major_locator(mdates.YearLocator())
+        ax.xaxis.set_minor_locator(mdates.MonthLocator())
+
+    if time_unit == "Month":
+        ax.xaxis.set_major_locator(mdates.MonthLocator())
+        ax.xaxis.set_minor_locator(mdates.WeekdayLocator())
+
+    if time_unit == "Weekday":
+        ax.xaxis.set_major_locator(mdates.WeekdayLocator())
+        ax.xaxis.set_minor_locator(mdates.DayLocator())
+
+    if time_unit == "Day":
+        ax.xaxis.set_major_locator(mdates.DayLocator())
+        ax.xaxis.set_minor_locator(mdates.HourLocator())
+
+    if time_unit == "Hour":
+        ax.xaxis.set_major_locator(mdates.HourLocator())
+        ax.xaxis.set_minor_locator(mdates.MinuteLocator())
+
+    ax.tick_params(axis="x", rotation=rot)
+    ax.grid(which="both")
+    ax.grid(which="minor", alpha=0.6, linestyle=":")
+    ax.grid(which="major", alpha=0.8, linestyle="--")
+
+    legend_elements = [
+        Line2D(
+            [0],
+            [0],
+            marker="o",
+            color=color2,
+            label="Current data",
+            linestyle="none",
+        ),
+        Line2D(
+            [0],
+            [0],
+            marker="o",
+            color=color1,
+            label="Imputed data",
+            linestyle="none",
+        ),
+    ]
+    ax.legend(handles=legend_elements, loc="upper right")
+
+    return fig
+
+
 def save_figure(
     fig,
     file_name,
@@ -151,3 +313,102 @@ def save_figure(
     fig.savefig(f"{base_name}.png")
     fig.savefig(f"{base_name}.pdf")
     fig.savefig(f"{base_name}.svg")
+
+
+def heat_map(X, y, colors="Blues"):
+    """
+    Generates a correlation heatmap plot for a set of features and a target variable.
+
+    This function concatenates the feature DataFrame (X) and the target Series (y)
+    to compute and visualize the full pairwise correlation matrix using Seaborn.
+
+    Parameters
+    ----------
+    X : pd.DataFrame
+        The DataFrame containing the feature variables.
+    y : pd.Series or pd.DataFrame
+        The target variable (must be concatenable with X).
+    colors : str or matplotlib.colors.Colormap, optional
+        The colormap to use for the heatmap, passed to the 'cmap' argument
+        in seaborn.heatmap. Defaults to "Blues".
+
+        Note: For standard correlation matrices (which include negative values),
+        a diverging colormap (e.g., "coolwarm", "vlag") is usually recommended.
+
+    Returns
+    -------
+    matplotlib.figure.Figure
+        The generated Matplotlib figure object containing the heatmap.
+
+    Notes
+    -----
+    The heatmap displays the Pearson correlation coefficient rounded to two
+    decimal places and includes annotations for improved readability.
+    """
+    fig, ax = plt.subplots()
+    Z = pd.concat([X, y], axis=1)
+
+    ax = sns.heatmap(
+        Z.corr(),
+        cmap=colors,
+        annot=True,
+        linewidths=0.5,
+        fmt=".2f",
+        annot_kws={"size": 10},
+    )
+
+    return fig
+
+
+def corrfunc(x, y, ax=None, **kws):
+    """Plot the correlation coefficient in the top left hand corner of a plot."""
+    r, _ = pearsonr(x, y)
+    ax = ax or plt.gca()
+    ax.annotate(f"R = {r:.2f}", xy=(0.1, 0.9), fontsize=25, xycoords=ax.transAxes)
+
+
+def pair_plot(X, y):
+    """
+    Generates a cornered pair plot (scatterplot matrix) to visualize relationships
+    between features and the target variable.
+
+    The function combines the feature DataFrame (X) and the target Series (y)
+    and uses seaborn.pairplot to create a matrix of scatter plots and histograms.
+    It focuses on the lower triangular part (corner=True) and includes a
+    regression line for trend visualization.
+
+    Parameters
+    ----------
+    X : pd.DataFrame
+        The DataFrame containing the feature variables.
+    y : pd.Series or pd.DataFrame
+        The target variable (must be concatenable with X).
+
+    Returns
+    -------
+    matplotlib.figure.Figure
+        The generated Matplotlib Figure object containing the cornered pair plot.
+
+    Notes
+    -----
+    1. **Dependency:** This function requires a previously defined custom function
+       `corrfunc` to be available in the local namespace, as it is used via
+       `svm.map_lower()`. This custom function is typically used to display
+       correlation coefficients (e.g., Pearson's r) in the lower panel.
+    2. **Aesthetics:** Uses a regression line (`kind="reg"`) with custom color
+       (RED_LINES) to highlight linear relationships.
+    3. **Output:** The returned Figure object can be manipulated further
+       or saved using methods like `fig.savefig()`.
+    """
+    Z = pd.concat([X, y], axis=1)
+    svm = sns.pairplot(
+        Z,
+        corner=True,
+        kind="reg",
+        plot_kws={"line_kws": {"color": paper_colors["RED_LINES"]}},
+    )
+    svm.map_lower(corrfunc)
+
+    fig = svm.fig
+
+    return fig

{direl_ts_tool_kit-0.4.9.dist-info → direl_ts_tool_kit-0.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: direl-ts-tool-kit
-Version: 0.4.9
+Version: 0.6.0
 Summary: A toolbox for time series analysis and visualization.
 Home-page: https://gitlab.com/direl/direl_tool_kit
 Author: Diego Restrepo-Leal
@@ -18,6 +18,8 @@ Requires-Dist: pandas>=1.0.0
 Requires-Dist: numpy>=1.18.0
 Requires-Dist: matplotlib>=3.0.0
 Requires-Dist: openpyxl
+Requires-Dist: seaborn
+Requires-Dist: scipy
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -87,6 +89,14 @@ This function automatically sets major and minor time-based locators
 on the x-axis based on the specified time unit, and formats the y-axis
 to use scientific notation.
 
+#### plot_interpolation_analysis
+`plot_interpolation_analysis(df_original, variable, units="", method="polynomial", order=2, imputation_se=None, time_unit="Year", rot=90)`
+
+Performs interpolation on missing data (NaNs) in a specified column and
+plots the result, highlighting the imputed points with confidence intervals
+if the Imputation Standard Error (SE) is provided.
+
+
 #### save_figure
 `save_figure(fig, file_name, variable_name="", path="./")`
 
@@ -95,6 +105,26 @@ Saves a Matplotlib figure in three common high-quality formats (PNG, PDF, SVG).
 The function creates a consistent file name structure:
 {path}/{file_name}_{variable_name}.{extension}.
 
+#### heat_map
+`heat_map(X, y, colors="Blues")`
+
+Generates a correlation heatmap plot for a set of features and a target variable.
+
+This function concatenates the feature DataFrame (X) and the target Series (y)
+to compute and visualize the full pairwise correlation matrix using Seaborn.
+
+#### pair_plot
+`pair_plot(X, y)`
+
+Generates a cornered pair plot (scatterplot matrix) to visualize relationships
+between features and the target variable.
+
+The function combines the feature DataFrame (X) and the target Series (y)
+and uses seaborn.pairplot to create a matrix of scatter plots and histograms.
+It focuses on the lower triangular part (corner=True) and includes a
+regression line for trend visualization.
+
+
 # Examples
 - [Example 1](https://gitlab.com/direl/direl_tool_kit/-/blob/main/example/example_01.md?ref_type=heads)
 - [Example 2](https://gitlab.com/direl/direl_tool_kit/-/blob/main/example/example_02.md?ref_type=heads)

direl_ts_tool_kit-0.6.0.dist-info/RECORD

@@ -0,0 +1,11 @@
+direl_ts_tool_kit/__init__.py,sha256=W99Wd3BeEFKOxT51TApURElbDJvqIjD8u_-qDoCYSJ0,94
+direl_ts_tool_kit/plot/__init__.py,sha256=CMwyv-kiE74nwr3MJPL7gWIJmcfZ8UQCRu7mBGGQ4rI,49
+direl_ts_tool_kit/plot/plot_style.py,sha256=5YxoLXlYvzleTnBEGPwCmHQIJ0S96KPJspq_n-qMvpw,1069
+direl_ts_tool_kit/plot/plot_ts.py,sha256=D1doDV24eKOFD7vxZUE6QRx-kTRPPjmbxcGOnvdVjKQ,12982
+direl_ts_tool_kit/utilities/__init__.py,sha256=jMtxYZUtwlhgI99sxe_8MMzsDnxtbTP7Ivh9tUOeIwQ,25
+direl_ts_tool_kit/utilities/data_prep.py,sha256=k3eOwQEEd5mxy2DtT_Gdo7BhkzEmSQqvMJ89y8mH5CQ,6024
+direl_ts_tool_kit-0.6.0.dist-info/licenses/LICENCE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+direl_ts_tool_kit-0.6.0.dist-info/METADATA,sha256=4G6DKqzMbNny1JE26bGSUuX5zpDqf-4VDuvjwgMZjLI,4883
+direl_ts_tool_kit-0.6.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+direl_ts_tool_kit-0.6.0.dist-info/top_level.txt,sha256=vMCRudnGnsdRg_6fUftnG8PF2Y1m0bjBDMf3pCAp6bc,18
+direl_ts_tool_kit-0.6.0.dist-info/RECORD,,

direl_ts_tool_kit-0.4.9.dist-info/RECORD

@@ -1,11 +0,0 @@
-direl_ts_tool_kit/__init__.py,sha256=W99Wd3BeEFKOxT51TApURElbDJvqIjD8u_-qDoCYSJ0,94
-direl_ts_tool_kit/plot/__init__.py,sha256=CMwyv-kiE74nwr3MJPL7gWIJmcfZ8UQCRu7mBGGQ4rI,49
-direl_ts_tool_kit/plot/plot_style.py,sha256=vhzcDa3LzgkHuy-GnliofGZ8TDntkm3_1C5kgl2Gx3E,1010
-direl_ts_tool_kit/plot/plot_ts.py,sha256=Fi_J-5qyDxcR-Z6sRHksn1e5QZcKqITGbpH3-bAX-Jw,5015
-direl_ts_tool_kit/utilities/__init__.py,sha256=jMtxYZUtwlhgI99sxe_8MMzsDnxtbTP7Ivh9tUOeIwQ,25
-direl_ts_tool_kit/utilities/data_prep.py,sha256=k3eOwQEEd5mxy2DtT_Gdo7BhkzEmSQqvMJ89y8mH5CQ,6024
-direl_ts_tool_kit-0.4.9.dist-info/licenses/LICENCE,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-direl_ts_tool_kit-0.4.9.dist-info/METADATA,sha256=CrRTdibENrgqBksrJVNTWR-Kt9C8uUAgpR5hwBK3bdI,3757
-direl_ts_tool_kit-0.4.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-direl_ts_tool_kit-0.4.9.dist-info/top_level.txt,sha256=vMCRudnGnsdRg_6fUftnG8PF2Y1m0bjBDMf3pCAp6bc,18
-direl_ts_tool_kit-0.4.9.dist-info/RECORD,,