xlin 0.1.20__py2.py3-none-any.whl → 0.1.22__py2.py3-none-any.whl

xlin/read_as_dataframe.py

@@ -13,7 +13,7 @@ from xlin.xls2xlsx import is_xslx
 
 
 def read_as_dataframe(
-    filepath: Union[str, Path],
+    filepath: Union[str, Path, list[str], list[Path]],
     sheet_name: Optional[str] = None,
     fill_empty_str_to_na=True,
     filter=lambda x: True,
@@ -21,11 +21,9 @@ def read_as_dataframe(
     """
     读取文件为表格。如果是文件夹，则读取文件夹下的所有文件为表格并拼接
     """
-    filepath = Path(filepath)
-    if filepath.is_dir():
-        paths = ls(filepath, filter=filter, expand_all_subdir=True)
+    if isinstance(filepath, list):
         df_list = []
-        for path in paths:
+        for path in filepath:
             try:
                 df = read_as_dataframe(path, sheet_name, fill_empty_str_to_na, filter)
                 df["数据来源"] = path.name
@@ -36,6 +34,10 @@ def read_as_dataframe(
         if fill_empty_str_to_na:
             df.fillna("", inplace=True)
         return df
+    filepath = Path(filepath)
+    if filepath.is_dir():
+        paths = ls(filepath, filter=filter, expand_all_subdir=True)
+        return read_as_dataframe(paths, sheet_name, fill_empty_str_to_na, filter)
     filename = filepath.name
     if filename.endswith(".json") or filename.endswith(".jsonl"):
         try:

xlin/statistic.py

@@ -19,7 +19,7 @@ def bucket_count(length: List[int], step=50, skip_zero_count=False):
             continue
         if skip_zero_count and j == 0:
             continue
-        print(f"[{(i-1)*step}, {i*step})  {j}   {sum(grouped_count[:i+1])/len(length)*100:.2f}%")
+        print(f"[{(i-1)*step}, {i*step})  {j}   {sum(grouped_count[:i+1])/len(length)*100:.4f}%")
         x.append((i - 1) * step)
         y.append(j)
     return x, y
@@ -73,22 +73,22 @@ def draw_histogram(data: list[int], bins=30, title="Data Distribution Analysis")
     plt.plot(x_vals, kde(x_vals), color="navy", linewidth=2, label="KDE Curve")
 
     # 添加统计线
-    plt.axvline(mean, color="red", linestyle="--", linewidth=2, label=f"Mean ({mean:.2f})")
-    plt.axvline(median, color="green", linestyle="-.", linewidth=2, label=f"Median ({median:.2f})")
-    plt.axvspan(mean - std, mean + std, color="orange", alpha=0.1, label=f"±1 Std.Dev ({std:.2f})")
+    plt.axvline(mean, color="red", linestyle="--", linewidth=2, label=f"Mean ({mean:.4f})")
+    plt.axvline(median, color="green", linestyle="-.", linewidth=2, label=f"Median ({median:.4f})")
+    plt.axvspan(mean - std, mean + std, color="orange", alpha=0.1, label=f"±1 Std.Dev ({std:.4f})")
 
     # 添加四分位线
-    plt.axvline(q25, color="purple", linestyle=":", alpha=0.8, label=f"25th Percentile ({q25:.2f})")
-    plt.axvline(q75, color="purple", linestyle=":", alpha=0.8, label=f"75th Percentile ({q75:.2f})")
-    plt.axvline(q80, color="purple", linestyle=":", alpha=0.8, label=f"80th Percentile ({q80:.2f})")
-    plt.axvline(q90, color="purple", linestyle=":", alpha=0.8, label=f"90th Percentile ({q90:.2f})")
+    plt.axvline(q25, color="purple", linestyle=":", alpha=0.8, label=f"25th Percentile ({q25:.4f})")
+    plt.axvline(q75, color="purple", linestyle=":", alpha=0.8, label=f"75th Percentile ({q75:.4f})")
+    plt.axvline(q80, color="purple", linestyle=":", alpha=0.8, label=f"80th Percentile ({q80:.4f})")
+    plt.axvline(q90, color="purple", linestyle=":", alpha=0.8, label=f"90th Percentile ({q90:.4f})")
 
     # 添加统计摘要
     stats_text = f"""\
-Data Range: [{data_range[0]:.2f}, {data_range[1]:.2f}]
+Data Range: [{data_range[0]:.4f}, {data_range[1]:.4f}]
 Observations: {len(data):,}
-Standard Deviation: {std:.2f}
-IQR: {q75 - q25:.2f}
+Standard Deviation: {std:.4f}
+IQR: {q75 - q25:.4f}
 Skewness: {float((data - mean).mean()**3 / std**3):.4f}
 Kurtosis: {float((data - mean).mean()**4 / std**4):.4f}\
 """

{xlin-0.1.20.dist-info → xlin-0.1.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: xlin
-Version: 0.1.20
+Version: 0.1.22
 Summary: toolbox for LinXueyuan
 License: MIT
 Author: LinXueyuanStdio

{xlin-0.1.20.dist-info → xlin-0.1.22.dist-info}/RECORD

@@ -3,13 +3,13 @@ xlin/ischinese.py,sha256=Ia9IMQ6q-UHkdLwqS70L1fTnfSPbluFrv_I1UqsKquo,293
 xlin/jsonl.py,sha256=Ogn_9eIx1NPmI_hMvBVwuDTooJYDEJ8FTtViQ8zTVlQ,7618
 xlin/metric.py,sha256=N7wJ35y-C-IaBr1I1CJ_37lTG7gA69zmn9Xg6xSwKoI,1690
 xlin/multiprocess_mapping.py,sha256=dRXQoLaG1dK_qZ8B3bJblV0RKM2gqIeSW1EaOZbIdD0,14251
-xlin/read_as_dataframe.py,sha256=T8A4qk4Grof_WC_mNz4QVaWDQgJ103rUAQ8tsamm8SQ,8898
-xlin/statistic.py,sha256=i0Z1gbW2IYHCA0lb16w1Ncrk0Q7Q1Ttm0n4we-ki6II,9301
+xlin/read_as_dataframe.py,sha256=MqY57L7Wp9UoWTRlZLSBKQNaZa-dKw51-ufrKvHKf8s,9041
+xlin/statistic.py,sha256=WMZkPFJ5da0rqIJHabdjCbWmgzgCOIj_H6KM5SVF7H0,9301
 xlin/timing.py,sha256=XMT8dMcMolOMohDvAZOIM_BAiPMREhGQKnO1kc5s6PU,998
 xlin/util.py,sha256=TTWJaqF5D_r-gAZ_fj0kyHomvCagjwHXQZ2OPSgwd54,10976
 xlin/xls2xlsx.py,sha256=uSmXcDvIhi5Sq0LGidMXy0wErNBXdjaoa6EftYVjTXs,947
 xlin/yaml.py,sha256=kICi7G3Td5q2MaSXXt85qNTWoHMgjzt7pvn7r3C4dME,183
-xlin-0.1.20.dist-info/LICENSE,sha256=60ys6rRtc1dZOP8UjSUr9fAqhZudT3WpKe5WbMCralM,1066
-xlin-0.1.20.dist-info/METADATA,sha256=DW9S85CerwgeiPFFETvVEai0OmxdIcoKSt9UXvIg71s,1098
-xlin-0.1.20.dist-info/WHEEL,sha256=IrRNNNJ-uuL1ggO5qMvT1GGhQVdQU54d6ZpYqEZfEWo,92
-xlin-0.1.20.dist-info/RECORD,,
+xlin-0.1.22.dist-info/LICENSE,sha256=60ys6rRtc1dZOP8UjSUr9fAqhZudT3WpKe5WbMCralM,1066
+xlin-0.1.22.dist-info/METADATA,sha256=77itC4591plUaDbS6T01BmZqeZ3jkoXT9uHgsLTTeA8,1098
+xlin-0.1.22.dist-info/WHEEL,sha256=IrRNNNJ-uuL1ggO5qMvT1GGhQVdQU54d6ZpYqEZfEWo,92
+xlin-0.1.22.dist-info/RECORD,,