py2ls 0.2.4__tar.gz → 0.2.4.1__tar.gz

{py2ls-0.2.4 → py2ls-0.2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.2.4
+Version: 0.2.4.1
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com

{py2ls-0.2.4 → py2ls-0.2.4.1}/py2ls/ips.py

@@ -4478,16 +4478,22 @@ def df_astype(
         "second",
         "time",
         "week",
-        "date",
+        "date","day",
         "month",
         "year",
     ]
-    # correct the astype input
-    astype = strcmp(astype, astypes)[0]
-    print(f"converting {columns} as type: {astype}")
     # If inplace is False, make a copy of the DataFrame
     if not inplace:
         df = df.copy()
+    # correct the astype input
+    if isinstance(astype,str):
+        astype = strcmp(astype, astypes)[0]
+        print(f"converting {columns} as type: {astype}")
+    elif isinstance(astype,dict):
+        for col, dtype in astype.items():
+            dtype='date' if dtype=="day" else dtype
+            df["col"]=df["col"].adtype(strcmp(dtype, astypes)[0])
+        return 
     # If columns is None, apply to all columns
     if columns is None:
         columns = df.columns
@@ -4523,7 +4529,7 @@ def df_astype(
                         df.iloc[:, column] = df.iloc[:, column].dt.month
                     elif astype == "year":
                         df.iloc[:, column] = df.iloc[:, column].dt.year
-                    elif astype == "date":
+                    elif astype == "date" or astype == "day":
                         df.iloc[:, column] = df.iloc[:, column].dt.date
                     elif astype == "hour":
                         df.iloc[:, column] = df.iloc[:, column].dt.hour

{py2ls-0.2.4 → py2ls-0.2.4.1}/py2ls/plot.py

@@ -10,7 +10,7 @@ from cycler import cycler
 import logging
 import os
 import re
-
+from typing import List, Optional, Union
 from .ips import fsave, fload, mkdir, listdir, figsave, strcmp, unique, get_os, ssplit
 from .stats import *
 from .netfinder import get_soup, fetch
@@ -152,6 +152,36 @@ def heatmap(
     yticklabels=True,  # Show row labels
     **kwargs,
 ):
+    """
+    plot heatmap or clustermap for a given dataset (DataFrame).
+
+    Parameters:
+    - data (pd.DataFrame): The input data to visualize.
+    - ax (matplotlib.Axes, optional): Axis object to plot on. If None and cluster=False, a new axis is created.
+    - kind (str, default="corr"): Type of heatmap to plot. Options:
+        - "corr": Correlation heatmap based on numeric columns.
+        - "direct": Direct visualization of the numeric data.
+        - "pivot": Creates a heatmap using the `pivot_table` method.
+    - columns (str or list, default="all"): Columns to include in the heatmap. For pivoting, this specifies the 'columns' argument.
+    - index (str, optional): For pivot heatmap, sets the 'index' argument.
+    - values (str, optional): For pivot heatmap, sets the 'values' argument.
+    - tri (str, default="u"): Specifies whether to show the 'upper' or 'lower' triangle in the heatmap.
+    - mask (bool, default=True): Whether to mask half of the correlation matrix.
+    - k (int, default=1): Controls how much of the triangle is masked in correlation heatmaps.
+    - annot (bool, default=True): If True, writes the data values in each cell.
+    - cmap (str, default="coolwarm"): The colormap for the heatmap.
+    - fmt (str, default=".2f"): String formatting code for annotating cells.
+    - cluster (bool, default=False): If True, a clustermap with hierarchical clustering is plotted.
+    - inplace (bool, default=False): If True, modifies the original data. Not currently used.
+    - figsize (tuple, default=(10, 8)): Size of the figure for the heatmap.
+    - row_cluster (bool, default=True): Perform clustering on rows.
+    - col_cluster (bool, default=True): Perform clustering on columns.
+    - dendrogram_ratio (tuple, default=(0.2, 0.1)): Adjust the size of the dendrograms.
+    - cbar_pos (tuple, default=(0.02, 1, 0.02, 0.1)): Adjust the position of the colorbar.
+    - xticklabels (bool, default=True): Show or hide the column labels.
+    - yticklabels (bool, default=True): Show or hide the row labels.
+    - **kwargs: Additional arguments passed to `sns.heatmap` or `sns.clustermap`.
+    """
     if ax is None and not cluster:
         ax = plt.gca()
     # Select numeric columns or specific subset of columns
@@ -162,7 +192,8 @@ def heatmap(
 
     kinds = ["corr", "direct", "pivot"]
     kind = strcmp(kind, kinds)[0]
-    if kind == "corr":
+    print(kind)
+    if "corr" in kind:  # correlation
         # Compute the correlation matrix
         data4heatmap = df_numeric.corr()
         # Generate mask for the upper triangle if mask is True
@@ -254,11 +285,26 @@ def heatmap(
             )
             # Return the Axes object for further customization if needed
             return ax
-    elif kind == "direct":
+    elif "dir" in kind:  # direct
         data4heatmap = df_numeric
-    elif kind == "pivot":
-        print('need 3 param: e.g., index="Task", columns="Model", values="Score"')
-        data4heatmap = data.pivot(index=index, columns=columns, values=values)
+    elif "pi" in kind:  # pivot
+        try:
+            print(
+                f'pivot: \n\tneed at least 3 param: e.g., index="Task", columns="Model", values="Score"'
+            )
+            data4heatmap = data.pivot(index=index, columns=columns, values=values)
+        except:
+            print(
+                f'pivot_table: \n\tneed at least 4 param: e.g., index="Task", columns="Model", values="Score",aggfunc="mean"'
+            )
+            aggfunc = "mean"
+            for k_, v_ in kwargs.items():
+                if "agg" in k_.lower():
+                    aggfunc = v_
+            kwargs.pop(k_, None)
+            data4heatmap = data.pivot_table(
+                index=index, columns=columns, values=values, aggfunc=aggfunc
+            )
     else:
         print(f'"{kind}" is not supported')
     # Remove conflicting kwargs
@@ -2873,13 +2919,26 @@ def plot_xy(
     x=None,
     y=None,
     ax=None,
-    kind: str = None,  # Specify the kind of plot
+    kind: Union(str, list) = None,  # Specify the kind of plot
+    verbose=False,
+    **kwargs,
+):
+    # You can call the original plotxy function if needed
+    # or simply replicate the functionality here
+    return plotxy(data, x, y, ax, kind, verbose, **kwargs)
+
+
+def plotxy(
+    data: pd.DataFrame = None,
+    x=None,
+    y=None,
+    ax=None,
+    kind: Union(str, list) = None,  # Specify the kind of plot
     verbose=False,
-    # kws_figsets:dict=None,
     **kwargs,
 ):
     """
-    e.g., plot_xy(data=data_log, x="Component_1", y="Component_2", hue="Cluster",kind='scater)
+    e.g., plotxy(data=data_log, x="Component_1", y="Component_2", hue="Cluster",kind='scater)
     Create a variety of plots based on the kind parameter.
 
     Parameters:
@@ -2942,10 +3001,10 @@ def plot_xy(
             kws_figsets = v_arg
             kwargs.pop(k_arg, None)
             break
-    kws_text = {}
+    kws_add_text = {}
     for k_arg, v_arg in kwargs.items():
-        if "add" in k_arg and all(["t" in k_arg, "x" in k_arg]):  # add_text
-            kws_text = v_arg
+        if "add" in k_arg and "text" in k_arg:  # add_text
+            kws_add_text = v_arg
             kwargs.pop(k_arg, None)
             break
 
@@ -2993,6 +3052,7 @@ def plot_xy(
             ax = stdshade(ax=ax, **kwargs)
         elif k == "scatterplot":
             kws_scatter = kwargs.pop("kws_scatter", kwargs)
+            hue = kwargs.pop("hue", None)
             palette = kws_scatter.pop(
                 "palette",
                 (
@@ -3029,7 +3089,8 @@ def plot_xy(
             ax = sns.rugplot(data=data, x=x, ax=ax, **kws_rug)
         elif k == "stripplot":
             kws_strip = kwargs.pop("kws_strip", kwargs)
-            ax = sns.stripplot(data=data, x=x, y=y, ax=ax, **kws_strip)
+            dodge = kws_strip.pop("dodge", True)
+            ax = sns.stripplot(data=data, x=x, y=y, ax=ax, dodge=dodge, **kws_strip)
         elif k == "swarmplot":
             kws_swarm = kwargs.pop("kws_swarm", kwargs)
             ax = sns.swarmplot(data=data, x=x, y=y, ax=ax, **kws_swarm)
@@ -3062,7 +3123,7 @@ def plot_xy(
             ax = sns.lineplot(ax=ax, data=data, x=x, y=y, **kws_line)
 
         figsets(ax=ax, **kws_figsets)
-        add_text(ax=ax, **kws_text)
+        add_text(ax=ax, **kws_add_text) if kws_add_text else None
         print(k, " ⤵ ")
         print(default_settings[k])
         print(

{py2ls-0.2.4 → py2ls-0.2.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "py2ls"
-version = "0.2.4"
+version = "0.2.4.1"
 description = "py(thon)2(too)ls"
 authors = ["Jianfeng <Jianfeng.Liu0413@gmail.com>"]
 readme = "README.md"