pandas-plots 0.15.10__py3-none-any.whl → 0.15.12__py3-none-any.whl

pandas_plots/hlp.py

@@ -21,49 +21,44 @@ from PIL import Image
 
 URL_REGEX = r"^(?:http|ftp)s?://"  # https://stackoverflow.com/a/1617386
 
-def mean_confidence_interval(data, confidence=0.95, use_median=False, n_bootstraps=1000):
+
+def mean_confidence_interval(df, confidence=0.95, use_median=False):
     """
-    Calculate the mean or median and confidence interval.
-    For median, uses bootstrapping for a more robust confidence interval.
+    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
 
     Parameters:
-    data (array-like): The input data.
+    df (array-like): The input dataframe.
     confidence (float, optional): The confidence level for the interval. Defaults to 0.95.
-    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.
+    use_median (bool, optional): If True, calculates median and confidence interval instead of mean. Defaults to False.
 
     Returns:
-    tuple: A tuple containing the central value (mean or median), margin of error, lower bound, and upper bound.
+    tuple: A tuple containing the central value (mean or median), interval, lower bound, and upper bound.
     """
-    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)
+    df = to_series(df)
+    if df is None:
+        return None
+    a = 1.0 * np.array(df)
     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)
-        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
+        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
     else:
-        mean = np.mean(a)
-        if n <= 1:
-            return mean, np.nan, np.nan, np.nan
-        se = scipy.stats.sem(a)
+        mean, se = np.mean(a), 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-0.15.10.dist-info → pandas_plots-0.15.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: pandas-plots
-Version: 0.15.10
+Version: 0.15.12
 Summary: A collection of helper for table handling and visualization
 Keywords: tables,pivot,plotly,venn,plot,vizualization
 Author: smeisegeier

pandas_plots-0.15.12.dist-info/RECORD

@@ -0,0 +1,8 @@
+pandas_plots/__init__.py,sha256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855,0
+pandas_plots/hlp.py,sha256=912aa818c11a3ad0bde30b534bb08c157320a6dbfedad48e31fe599bb7ae8692,20838
+pandas_plots/pls.py,sha256=66afca26f49471609fbb3f870f0d63e12e40be9c14ce83665cd03f69901abe15,65548
+pandas_plots/tbl.py,sha256=489d92b8b4b2664dae89addda1512da8accb5a63e6e2710c58e9507c95a414f1,33571
+pandas_plots/ven.py,sha256=db1dc00a8daf49f3b7aba7eff94743434875489cadf160a1046804e520c27429,11673
+pandas_plots-0.15.12.dist-info/WHEEL,sha256=a51d7af6bb8356f1000fb3d205aba975eca53e14c9e011c620094d822eb4863c,79
+pandas_plots-0.15.12.dist-info/METADATA,sha256=2b6fcda11a6ea6b648fbb6d0854607a4382c9c7d9c95fc109c51322cb16cd57c,8000
+pandas_plots-0.15.12.dist-info/RECORD,,

{pandas_plots-0.15.10.dist-info → pandas_plots-0.15.12.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: uv 0.8.9
+Generator: uv 0.8.10
 Root-Is-Purelib: true
 Tag: py3-none-any

pandas_plots-0.15.10.dist-info/RECORD

@@ -1,9 +0,0 @@
-pandas_plots/.DS_Store,sha256=e90dd27d76d30869e4b3244fc211ad13e2acf715d00902d8cc1501e123fbf26d,6148
-pandas_plots/__init__.py,sha256=e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855,0
-pandas_plots/hlp.py,sha256=cfcaeb54d6c7f6a32885d5cf4fe164b0ff959133a32346c6163e3b4b0e69dda6,21141
-pandas_plots/pls.py,sha256=66afca26f49471609fbb3f870f0d63e12e40be9c14ce83665cd03f69901abe15,65548
-pandas_plots/tbl.py,sha256=489d92b8b4b2664dae89addda1512da8accb5a63e6e2710c58e9507c95a414f1,33571
-pandas_plots/ven.py,sha256=db1dc00a8daf49f3b7aba7eff94743434875489cadf160a1046804e520c27429,11673
-pandas_plots-0.15.10.dist-info/WHEEL,sha256=2b400f346628f0064eb5bbf656b39df8dfcb092437ab08244409d295749b81a3,78
-pandas_plots-0.15.10.dist-info/METADATA,sha256=284ec43a99fc30ba4d564cd114475a743cce675fa21cf1bdfb265d9aa1644ce0,8000
-pandas_plots-0.15.10.dist-info/RECORD,,