pandas-plots 0.12.24__py3-none-any.whl → 0.12.26__py3-none-any.whl

pandas_plots/hlp.py

@@ -21,44 +21,49 @@ from PIL import Image
 
 URL_REGEX = r"^(?:http|ftp)s?://"  # https://stackoverflow.com/a/1617386
 
-
-def mean_confidence_interval(df, confidence=0.95, use_median=False):
+def mean_confidence_interval(data, confidence=0.95, use_median=False, n_bootstraps=1000):
     """
-    Calculate the mean or median and confidence interval of the input dataframe.
-    Source: https://stackoverflow.com/questions/15033511/compute-a-confidence-interval-from-sample-data
+    Calculate the mean or median and confidence interval.
+    For median, uses bootstrapping for a more robust confidence interval.
 
     Parameters:
-    df (array-like): The input dataframe.
+    data (array-like): The input data.
     confidence (float, optional): The confidence level for the interval. Defaults to 0.95.
-    use_median (bool, optional): If True, calculates median and confidence interval instead of mean. Defaults to False.
+    use_median (bool, optional): If True, calculates median and its confidence interval. Defaults to False.
+    n_bootstraps (int, optional): Number of bootstrap samples for median CI. Only used if use_median is True.
 
     Returns:
-    tuple: A tuple containing the central value (mean or median), interval, lower bound, and upper bound.
+    tuple: A tuple containing the central value (mean or median), margin of error, lower bound, and upper bound.
     """
-    df = to_series(df)
-    if df is None:
-        return None
-    a = 1.0 * np.array(df)
+    data = to_series(data)
+    if data is None or len(data) == 0:
+        return np.nan, np.nan, np.nan, np.nan
+    a = 1.0 * np.array(data)
     n = len(a)
 
     if use_median:
+        if n < 2: # Cannot bootstrap with n < 2
+            return np.median(a), np.nan, np.nan, np.nan
+
+        bootstrapped_medians = []
+        for _ in range(n_bootstraps):
+            sample = np.random.choice(a, size=n, replace=True)
+            bootstrapped_medians.append(np.median(sample))
+
         median = np.median(a)
-        se = 1.253 * scipy.stats.sem(a)  # Approximate standard error for median
-        margin = se * scipy.stats.t.ppf((1 + confidence) / 2.0, n - 1)
-        return median, margin, median - margin, median + margin
+        alpha = (1 - confidence) / 2
+        lower_bound = np.percentile(bootstrapped_medians, alpha * 100)
+        upper_bound = np.percentile(bootstrapped_medians, (1 - alpha) * 100)
+        margin = (upper_bound - lower_bound) / 2 # Simple approximation for margin based on interval width
+        return median, margin, lower_bound, upper_bound
     else:
-        mean, se = np.mean(a), scipy.stats.sem(a)
+        mean = np.mean(a)
+        if n <= 1:
+            return mean, np.nan, np.nan, np.nan
+        se = scipy.stats.sem(a)
         margin = se * scipy.stats.t.ppf((1 + confidence) / 2.0, n - 1)
         return mean, margin, mean - margin, mean + margin
 
-    # # * Alternative
-    # # from statistics import NormalDist
-    # def confidence_interval(data, confidence=0.95):
-    #     dist = NormalDist.from_samples(data)
-    #     z = NormalDist().inv_cdf((1 + confidence) / 2.)
-    #     h = dist.stdev * z / ((len(data) - 1) ** .5)
-    #     return dist.mean - h, dist.mean + h
-
 
 def to_series(df) -> pd.Series | None:
     """

pandas_plots/pls.py

@@ -563,9 +563,10 @@ def plot_bars(
 
     # * ensure df is grouped to prevent false aggregations, reset index to return df
     if use_ci:
-        # * grouping is smoother on df than on series
-        df = (
-            df_in.groupby(
+# * grouping is smoother on df than on series
+        df = (df_in
+            # ? dont dropna() here, this biases the input data
+            .groupby(
                 col_index,
                 dropna=False,
             )
@@ -576,10 +577,11 @@ def plot_bars(
             )
             .reset_index()
         )
-        # * enforce vertical bars when using ci
+        # * enforce vertical bars **when using ci**, normalize=False, dropna=True, set empty margin to 0 to avoid dropping the bar
         orientation = "v"
         normalize = False
         dropna = True
+        df.margin.fillna(0, inplace=True)
     else:
         df = df_in.groupby(col_index, dropna=dropna)[col_name].sum().reset_index()
 
@@ -591,6 +593,7 @@ def plot_bars(
     else:
         df = df.fillna("<NA>")
 
+
     # * get n, col1 now is always numeric
     n = df[df.columns[1]].sum()
     n_len = len(df_in)
@@ -1116,6 +1119,8 @@ def plot_box(
     return fig
 
 
+
+
 def plot_boxes(
     df: pd.DataFrame,
     caption: str = None,
@@ -1164,14 +1169,9 @@ def plot_boxes(
     xlvl2 = 0
     xlvl3 = 50
 
-    # * not working
-    # yspan_seg = (df.iloc[:, 1].max() - df.iloc[:, 1].max()) * .05
-    # ylvl1 = -yspan_seg
-    # ylvl2 = 0
-    # ylvl3 = yspan_seg
-
     # * unique items
-    items = df.iloc[:, 0].unique()
+    # Sort the unique items alphabetically
+    items = sorted(df.iloc[:, 0].unique())
 
     caption = _set_caption(caption)
     log_str = " (log-scale)" if use_log else ""
@@ -1196,6 +1196,9 @@ def plot_boxes(
         ),
     )
 
+    # * Set the order of the x-axis categories
+    fig.update_xaxes(categoryorder="array", categoryarray=items)
+
     # * yshift is trivial
     YS = 0
 
@@ -1273,6 +1276,7 @@ def plot_boxes(
 
     return fig
 
+
 def plot_facet_stacked_bars(
     df: pd.DataFrame,
     subplots_per_row: int = 4,

{pandas_plots-0.12.24.dist-info → pandas_plots-0.12.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pandas-plots
-Version: 0.12.24
+Version: 0.12.26
 Summary: A collection of helper for table handling and visualization
 Home-page: https://github.com/smeisegeier/pandas-plots
 Author: smeisegeier
@@ -49,7 +49,7 @@ pip install pandas-plots -U
 include in python
 
 ```python
-from pandas_plots import tbl, pls, ven, hlp, pii
+from pandas_plots import tbl, pls, ven, hlp
 ```
 
 ## example
@@ -119,9 +119,6 @@ tbl.show_num_df(
   - `add_measures_to_pyg_config()` adds measures to a pygwalker config file to avoid frequent manual update
 <br>
 
-- `pii` has routines for handling of personally identifiable information
-  - `remove_pii()` logs and deletes pii from a series
-
 > note: theme setting can be controlled through all functions by setting the environment variable `THEME` to either light or dark
 
 ## more examples

pandas_plots-0.12.26.dist-info/RECORD

@@ -0,0 +1,10 @@
+pandas_plots/hlp.py,sha256=z8rrVNbH9qMohdXPT-FksP-VkTOjI0bGFj47Sw5p3aY,21141
+pandas_plots/pls.py,sha256=wFRQurKtG1GrZK8Z7eHfi7OwrbfM9Xitk_7PolWc_Dk,48823
+pandas_plots/tbl.py,sha256=RJWBHeKGTAhGpVCY57TsS_dYR-FpInP-TOsKW_tU4V4,32556
+pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
+pandas_plots-0.12.26.dist-info/licenses/LICENSE,sha256=ltLbQWUCs-GBQlTPXbt5nHNBE9U5LzjjoS1Y8hHETM4,1051
+pandas_plots-0.12.26.dist-info/METADATA,sha256=GD2hSPNemqOdnXr96lGvAr3LZQCpm0pjKgv78yd3IKk,7431
+pandas_plots-0.12.26.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+pandas_plots-0.12.26.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
+pandas_plots-0.12.26.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
+pandas_plots-0.12.26.dist-info/RECORD,,

{pandas_plots-0.12.24.dist-info → pandas_plots-0.12.26.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.8.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

pandas_plots/pii.py

@@ -1,76 +0,0 @@
-import pandas as pd
-import re
-
-
-def remove_pii(
-    series: pd.Series,
-    verbose: bool = True,
-    logging: bool = False,
-    custom_regex="",
-) -> pd.Index:
-    """
-    Remove personally identifiable information (PII) from the given column.
-
-    Parameters:
-    - series: A pandas Series representing a column in a DataFrame.
-    - verbose: If True, print pii items
-    - logging: If True, write pii items into the file .pii.log
-    - custom_regex: Regex that is injected into detection
-
-    Returns:
-    - index object with indexes of all pii items
-    
-    Remarks:
-    - df.drop(axis=0, index=result, inplace=True)
-    """
-
-    # * reject empty columns
-    assert len(series) > 0
-
-    col = series.copy()
-
-    # * na must be dropped to ensure processsing
-    col.dropna(inplace=True)
-
-    # * find terms
-    _terms = frozenset(["lösch", "herr", "frau", "strasse", "klinik"])
-    idx_terms = col[
-        col.str.contains(
-            "|".join(_terms),
-            case=False,
-            regex=True,
-        )
-    ].index
-
-    # # * optional: search for terms in whole df
-    # df.apply(lambda row: row.astype(str).str.contains('test', case=False, regex=True).any(), axis=1)
-
-    # # * find dates
-    ptr_date = r"\d{2}\.\d{2}\.\d{4}"
-    idx_date = col[col.str.contains(ptr_date, regex=True)].index
-
-    # * dr
-    ptr_dr = r"[D|d][R|r]\. | Fr\. | Hr\. | PD "
-    idx_dr = col[col.str.contains(ptr_dr, regex=True)].index
-
-    # * custom
-    idx_custom = (
-        col[col.str.contains(custom_regex, regex=True)].index
-        if custom_regex
-        else pd.Index([])
-    )
-
-    idx_all = idx_terms.union(idx_date).union(idx_dr).union(idx_custom)
-
-    if verbose:
-        # print(f"found: {idx_dr.__len__()} dr | {idx_date.__len__()} date | {idx_terms.__len__()} terms")
-        print(f"found {idx_all.__len__():_} pii items:")
-        print(col.loc[idx_all].tolist())
-
-    if logging:  # Assuming logging is defined and has the correct value
-        data = col.loc[idx_all]  # Assuming col and idx_all are defined
-        with open(".pii.log", "w") as f:
-            # ! when using str(), it will give only a summary!
-            f.write(data.to_string(index=True))
-
-    return idx_all

pandas_plots-0.12.24.dist-info/RECORD

@@ -1,11 +0,0 @@
-pandas_plots/hlp.py,sha256=kSqoGMEaOtC94wtTS7CMFXMgptv-2tSOMf5Zm7euhpI,20838
-pandas_plots/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots/pls.py,sha256=jFsHvjG8fvLBdHpaYOX_5TgpDrcA5bMWjAUtXb6bVXo,48629
-pandas_plots/tbl.py,sha256=RJWBHeKGTAhGpVCY57TsS_dYR-FpInP-TOsKW_tU4V4,32556
-pandas_plots/ven.py,sha256=2x3ACo2vSfO3q6fv-UdDQ0h1SJyt8WChBGgE5SDCdCk,11673
-pandas_plots-0.12.24.dist-info/licenses/LICENSE,sha256=ltLbQWUCs-GBQlTPXbt5nHNBE9U5LzjjoS1Y8hHETM4,1051
-pandas_plots-0.12.24.dist-info/METADATA,sha256=5519ufLPkBZEaylDrN6lC-D5Rtc7xr4tGQVNDtW_5Ms,7564
-pandas_plots-0.12.24.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-pandas_plots-0.12.24.dist-info/pii.py,sha256=2WKE-W9s285jPdsTqCgt1uxuW4lj1PYCVOYB2fYDNwQ,2195
-pandas_plots-0.12.24.dist-info/top_level.txt,sha256=XnaNuIHBqMmCeh_U7nKOYTwFue_SIA0wxuDgdPmnnSk,13
-pandas_plots-0.12.24.dist-info/RECORD,,