py2ls 0.2.4.9.4__py3-none-any.whl → 0.2.4.9.5__py3-none-any.whl

py2ls/stats.py

@@ -37,7 +37,7 @@ def FuncStars(
     report=None,
     report_scale=-0.1,
     report_loc=None,
-    **kwargs
+    **kwargs,
 ):
     if ax is None:
         ax = plt.gca()
@@ -53,7 +53,7 @@ def FuncStars(
     if y_loc is None:
         y_loc = np.min(ylim) + yscale * (np.max(ylim) - np.min(ylim))
     else:
-        y_loc=y_loc+(1-yscale) * np.abs(np.diff(ylim))+0.1 *y_loc
+        y_loc = y_loc + (1 - yscale) * np.abs(np.diff(ylim)) + 0.1 * y_loc
     xcenter = np.mean([x1, x2])
     if pval is not None:
         # ns / *
@@ -79,7 +79,7 @@ def FuncStars(
                 y_loc,
                 symbol,
                 ha="center",
-                va="top",#"center_baseline",
+                va="top",  # "center_baseline",
                 fontsize=fontsize,
                 fontname=fontname,
                 color=symbolcolor,
@@ -90,7 +90,7 @@ def FuncStars(
                 y_loc,
                 symbol * 2,
                 ha="center",
-                va="top",#"center_baseline",
+                va="top",  # "center_baseline",
                 fontsize=fontsize,
                 fontname=fontname,
                 color=symbolcolor,
@@ -101,7 +101,7 @@ def FuncStars(
                 y_loc,
                 symbol * 3,
                 ha="center",
-                va="top",#"center_baseline",
+                va="top",  # "center_baseline",
                 fontsize=fontsize,
                 fontname=fontname,
                 color=symbolcolor,
@@ -111,7 +111,10 @@ def FuncStars(
             # horizontal line
             if yscale <= 0.99:
                 ax.plot(
-                    [x1 + np.abs(np.diff(xlim)) * 0.01, x2 - np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         y_loc - np.abs(np.diff(ylim)) * 0.03,
                         y_loc - np.abs(np.diff(ylim)) * 0.03,
@@ -122,7 +125,10 @@ def FuncStars(
                 )
                 # vertical line
                 ax.plot(
-                    [x1 + np.abs(np.diff(xlim)) * 0.01, x1 + np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         y_loc - np.abs(np.diff(ylim)) * tailindicator[0],
                         y_loc - np.abs(np.diff(ylim)) * 0.03,
@@ -132,7 +138,10 @@ def FuncStars(
                     linewidth=linewidth,
                 )
                 ax.plot(
-                    [x2 - np.abs(np.diff(xlim)) * 0.01, x2 - np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         y_loc - np.abs(np.diff(ylim)) * tailindicator[1],
                         y_loc - np.abs(np.diff(ylim)) * 0.03,
@@ -143,7 +152,10 @@ def FuncStars(
                 )
             else:
                 ax.plot(
-                    [x1 + np.abs(np.diff(xlim)) * 0.01, x2 - np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         np.min(ylim)
                         + 0.95 * (np.max(ylim) - np.min(ylim))
@@ -158,7 +170,10 @@ def FuncStars(
                 )
                 # vertical line
                 ax.plot(
-                    [x1 + np.abs(np.diff(xlim)) * 0.01, x1 + np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                        x1 + np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         np.min(ylim)
                         + 0.95 * (np.max(ylim) - np.min(ylim))
@@ -172,7 +187,10 @@ def FuncStars(
                     linewidth=linewidth,
                 )
                 ax.plot(
-                    [x2 - np.abs(np.diff(xlim)) * 0.01, x2 - np.abs(np.diff(xlim)) * 0.01],
+                    [
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                        x2 - np.abs(np.diff(xlim)) * 0.01,
+                    ],
                     [
                         np.min(ylim)
                         + 0.95 * (np.max(ylim) - np.min(ylim))
@@ -312,9 +330,7 @@ def FuncCmpt(x1, x2, pmc="auto", pair="unpaired", verbose=True):
                 )
                 notes_stat = "paired t test"
                 # note: APA FORMAT
-                notes_APA = (
-                    f"t({sum([nX1-1])})={round(stat_value,3)},p={round(pval,3)}"
-                )
+                notes_APA = f"t({sum([nX1-1])})={round(stat_value,3)},p={round(pval,3)}"
         elif cfg_pmc == "non-parametric":
             if "np" in pair:  # Perform Mann-Whitney
                 stat_value, pval = stats.mannwhitneyu(
@@ -324,7 +340,9 @@ def FuncCmpt(x1, x2, pmc="auto", pair="unpaired", verbose=True):
                 if nX1 == nX2:
                     notes_APA = f"U(n={nX1})={round(stat_value,3)},p={round(pval,3)}"
                 else:
-                    notes_APA = f"U(n1={nX1},n2={nX2})={round(stat_value,3)},p={round(pval,3)}"
+                    notes_APA = (
+                        f"U(n1={nX1},n2={nX2})={round(stat_value,3)},p={round(pval,3)}"
+                    )
             elif "pa" in pair and "np" not in pair:  # Wilcoxon signed-rank test
                 stat_value, pval = stats.wilcoxon(
                     x1, x2, method="exact", nan_policy="omit"
@@ -333,7 +351,9 @@ def FuncCmpt(x1, x2, pmc="auto", pair="unpaired", verbose=True):
                 if nX1 == nX2:
                     notes_APA = f"Z(n={nX1})={round(stat_value,3)},p={round(pval,3)}"
                 else:
-                    notes_APA = f"Z(n1={nX1},n2={nX2})={round(stat_value,3)},p={round(pval,3)}"
+                    notes_APA = (
+                        f"Z(n1={nX1},n2={nX2})={round(stat_value,3)},p={round(pval,3)}"
+                    )
 
         # filling output
         output["stat"] = stat_value
@@ -408,7 +428,7 @@ def FuncMultiCmpt(
     subject=None,
     group=None,
     verbose=True,
-    post_hoc=False
+    post_hoc=False,
 ):
     if group is None:
         group = factor
@@ -520,12 +540,16 @@ def FuncMultiCmpt(
         if "np" in cfg_pair:  # 'unpaired'
             res_tab = run_kruskal(data, dv, factor)
             notes_stat = f"Non-parametric Kruskal: {data[factor].nunique()} Way ANOVA"
-            notes_APA = [f'H({res_tab.ddof1[0]},N={data.shape[0]})={round(res_tab.H[0],3)},p={round(res_tab["p-unc"][0],3)}']
+            notes_APA = [
+                f'H({res_tab.ddof1[0]},N={data.shape[0]})={round(res_tab.H[0],3)},p={round(res_tab["p-unc"][0],3)}'
+            ]
 
         elif "pa" in cfg_pair and "np" not in cfg_pair:  # 'paired'
             res_tab = run_friedman(data, dv, factor, subject, method="chisq")
             notes_stat = f"Non-parametric {data[factor].nunique()} Way Friedman repeated measures ANOVA"
-            notes_APA = [f'X^2({res_tab.ddof1[0]})={round(res_tab.Q[0],3)},p={round(res_tab["p-unc"][0],3)}']
+            notes_APA = [
+                f'X^2({res_tab.ddof1[0]})={round(res_tab.Q[0],3)},p={round(res_tab["p-unc"][0],3)}'
+            ]
 
     # =============================================================================
     # # Post-hoc
@@ -542,7 +566,7 @@ def FuncMultiCmpt(
     go_mix_within = factor if ("pa" in cfg_pair) or ("np" not in cfg_pair) else None
 
     if res_tab["p-unc"][0] <= 0.05:
-        post_hoc=True
+        post_hoc = True
     if post_hoc:
         # Pairwise Comparisons
         method_post_hoc = [
@@ -610,9 +634,9 @@ def FuncMultiCmpt(
     #     # filling output
     # =============================================================================
 
-    pd.set_option('display.max_columns', None)  # Show all columns
-    pd.set_option('display.max_colwidth', None)  # No limit on column width
-    pd.set_option('display.expand_frame_repr', False)  # Prevent line-wrapping
+    pd.set_option("display.max_columns", None)  # Show all columns
+    pd.set_option("display.max_colwidth", None)  # No limit on column width
+    pd.set_option("display.expand_frame_repr", False)  # Prevent line-wrapping
 
     output["stat"] = notes_stat
     # print(output['APA'])
@@ -627,7 +651,7 @@ def FuncMultiCmpt(
 def display_output(output: dict):
     if isinstance(output, pd.DataFrame):
         output = output.to_dict(orient="list")
-    # ['res_posthoc', 'stat', 'APA', 'pval', 'res_tab'] 
+    # ['res_posthoc', 'stat', 'APA', 'pval', 'res_tab']
 
     # ? show APA
     # print(f"\n\ndisplay stat_output")
@@ -641,7 +665,7 @@ def display_output(output: dict):
     except:
         pass
     try:
-        print(f"APA  ⤵\n{output["APA"][0]}  ⤵\npost-hoc analysis ⤵")
+        print(f"APA  ⤵\n{output['APA'][0]}  ⤵\npost-hoc analysis ⤵")
         display(output["res_posthoc"])
     except:
         pass
@@ -659,26 +683,27 @@ def corr_pair(pair):
 
 
 def check_normality(data, verbose=True):
-    if len(data)<=5000:
-        # Shapiro-Wilk test is designed to test the normality of a small sample, typically less than 5000 observations. 
+    if len(data) <= 5000:
+        # Shapiro-Wilk test is designed to test the normality of a small sample, typically less than 5000 observations.
         stat_shapiro, pval4norm = stats.shapiro(data)
-        method='Shapiro-Wilk test'
+        method = "Shapiro-Wilk test"
     else:
         from scipy.stats import kstest, zscore
-        data_scaled = zscore(data) # a standard normal distribution(mean=0,sd=1)
-        stat_kstest, pval4norm = kstest(data_scaled, 'norm')
-        method='Kolmogorov–Smirnov test'
+
+        data_scaled = zscore(data)  # a standard normal distribution(mean=0,sd=1)
+        stat_kstest, pval4norm = kstest(data_scaled, "norm")
+        method = "Kolmogorov–Smirnov test"
     if pval4norm >= 0.05:
         Normality = True
     else:
         Normality = False
     if verbose:
-            print(f"\'{method}' was used to test for normality")
-            (
-                print("\nnormally distributed")
-                if Normality
-                else print(f"\n NOT normally distributed\n")
-            )
+        print(f"'{method}' was used to test for normality")
+        (
+            print("\nnormally distributed")
+            if Normality
+            else print(f"\n NOT normally distributed\n")
+        )
     return Normality
 
 
@@ -714,7 +739,7 @@ def extract_apa(res_tab):
         for irow in range(res_tab.shape[0]):
             note_tmp = f'{res_tab.Source[irow]}:F{round(res_tab.ddof1[irow]),round(res_tab.ddof2[irow])}={round(res_tab.F[irow],3)},p={round(res_tab["p-unc"][irow],3)}'
             notes_APA.append(note_tmp)
-    elif "DF" in res_tab: 
+    elif "DF" in res_tab:
         for irow in range(res_tab.shape[0] - 1):
             note_tmp = f'{res_tab.Source[irow]}:F{round(res_tab.DF[irow]),round(res_tab.DF[res_tab.shape[0]-1])}={round(res_tab.F[irow],3)},p={round(res_tab["p-unc"][irow],3)}'
             notes_APA.append(note_tmp)
@@ -876,7 +901,7 @@ def df_wide_long(df):
     elif rows > columns:
         return "Long"
 
- 
+
 def sort_rows_move_nan(arr, sort=False):
     # Handle edge cases where all values are NaN
     if np.all(np.isnan(arr)):
@@ -917,7 +942,7 @@ def df2array(data: pd.DataFrame, x=None, y=None, hue=None, sort=False):
     if hue is None:
         a = []
         if sort:
-            cat_x=np.sort(data[x].unique().tolist()).tolist()
+            cat_x = np.sort(data[x].unique().tolist()).tolist()
         else:
             cat_x = data[x].unique().tolist()
         for i, x_ in enumerate(cat_x):
@@ -938,6 +963,7 @@ def df2array(data: pd.DataFrame, x=None, y=None, hue=None, sort=False):
                 a = padcat(a, new_, axis=0)
         return sort_rows_move_nan(a).T
 
+
 def array2df(data: np.ndarray):
     df = pd.DataFrame()
     df["group"] = (
@@ -949,6 +975,8 @@ def array2df(data: np.ndarray):
     )
     df["value"] = data.reshape(-1, 1, order="F")
     return df
+
+
 def padcat(*args, fill_value=np.nan, axis=1, order="row"):
     """
     Concatenate vectors with padding.

{py2ls-0.2.4.9.4.dist-info → py2ls-0.2.4.9.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: py2ls
-Version: 0.2.4.9.4
+Version: 0.2.4.9.5
 Summary: py(thon)2(too)ls
 Author: Jianfeng
 Author-email: Jianfeng.Liu0413@gmail.com
@@ -63,6 +63,7 @@ Requires-Dist: defusedxml (>=0.7.1)
 Requires-Dist: distlib (>=0.3.8)
 Requires-Dist: docopt (>=0.6.2)
 Requires-Dist: docx (>=0.2.4)
+Requires-Dist: duckduckgo-search (>=0.5.1,<0.6.0)
 Requires-Dist: dulwich (>=0.21.7)
 Requires-Dist: executing (>=2.0.1)
 Requires-Dist: faiss-cpu (>=1.8.0.post1)

{py2ls-0.2.4.9.4.dist-info → py2ls-0.2.4.9.5.dist-info}/RECORD

@@ -222,9 +222,9 @@ py2ls/ocr.py,sha256=5lhUbJufIKRSOL6wAWVLEo8TqMYSjoI_Q-IO-_4u3DE,31419
 py2ls/plot.py,sha256=LeQpTLvRHMDrQtU8yaeXEOgDdVm7KWLcAuRia6wWMYQ,167604
 py2ls/setuptools-70.1.0-py3-none-any.whl,sha256=2bi3cUVal8ip86s0SOvgspteEF8SKLukECi-EWmFomc,882588
 py2ls/sleep_events_detectors.py,sha256=bQA3HJqv5qnYKJJEIhCyhlDtkXQfIzqksnD0YRXso68,52145
-py2ls/stats.py,sha256=DMoJd8Z5YV9T1wB-4P52F5K5scfVK55DT8UP4Twcebo,38627
+py2ls/stats.py,sha256=qBn2rJmNa_QLLUqjwYqXUlGzqmW94sgA1bxJU2FC3r0,39175
 py2ls/translator.py,sha256=zBeq4pYZeroqw3DT-5g7uHfVqKd-EQptT6LJ-Adi8JY,34244
 py2ls/wb_detector.py,sha256=7y6TmBUj9exCZeIgBAJ_9hwuhkDh1x_-yg4dvNY1_GQ,6284
-py2ls-0.2.4.9.4.dist-info/METADATA,sha256=aIBMMfb9xGpBiqgc_C0z8AFd0xAV_wnJmsb22_NQSMw,20040
-py2ls-0.2.4.9.4.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-py2ls-0.2.4.9.4.dist-info/RECORD,,
+py2ls-0.2.4.9.5.dist-info/METADATA,sha256=9r2YCzit9C4tbEwsmPAC5uukE3vJ4w-jxnCw8b2flHo,20090
+py2ls-0.2.4.9.5.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+py2ls-0.2.4.9.5.dist-info/RECORD,,