halib 0.1.46__tar.gz → 0.1.48__tar.gz

{halib-0.1.46/halib.egg-info → halib-0.1.48}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: halib
-Version: 0.1.46
+Version: 0.1.48
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
@@ -15,6 +15,13 @@ License-File: LICENSE.txt
 
 Helper package for coding and automation
 
+**Version 0.1.48**
+
++ add `research` module to help with research tasks, including `benchquery` for benchmarking queries from dataframe
+
+**Version 0.1.47**
++ add `pprint_box` to print object/string in a box frame (like in `inspect`)
+
 **Version 0.1.46**
 + filter the warning message of `UserWarning: Unable to import Axes3D.`
 + auto_wrap_text for `fn_display_df` to avoid long text in the table

{halib-0.1.46 → halib-0.1.48}/README.md

@@ -1,5 +1,12 @@
 Helper package for coding and automation
 
+**Version 0.1.48**
+
++ add `research` module to help with research tasks, including `benchquery` for benchmarking queries from dataframe
+
+**Version 0.1.47**
++ add `pprint_box` to print object/string in a box frame (like in `inspect`)
+
 **Version 0.1.46**
 + filter the warning message of `UserWarning: Unable to import Axes3D.`
 + auto_wrap_text for `fn_display_df` to avoid long text in the table

{halib-0.1.46 → halib-0.1.48}/halib/__init__.py

@@ -20,6 +20,7 @@ __all__ = [
     "pd",
     "plt",
     "pprint",
+    "pprint_box",
     "px",
     "rcolor_all_str",
     "rcolor_palette_all",
@@ -32,7 +33,7 @@ __all__ = [
     "timebudget",
     "tqdm",
     "warnings",
-    "time"
+    "time",
 ]
 import warnings
 warnings.filterwarnings("ignore", message="Unable to import Axes3D")
@@ -53,7 +54,7 @@ from .system import cmd
 from .system import filesys as fs
 from .filetype import csvfile
 from .cuda import tcuda
-from .common import console, console_log, ConsoleLog, now_str, norm_str
+from .common import console, console_log, ConsoleLog, now_str, norm_str, pprint_box
 
 # for log
 from loguru import logger

{halib-0.1.46 → halib-0.1.48}/halib/common.py

@@ -1,7 +1,9 @@
 import arrow
 import re
 from rich.console import Console
-from rich.pretty import pprint
+from rich.pretty import pprint, Pretty
+from rich.panel import Panel
+import rich
 
 console = Console()
 
@@ -43,6 +45,16 @@ def norm_str(in_str):
     norm_string = norm_string.strip()
     return norm_string
 
+
+def pprint_box(obj, title="", border_style="green"):
+    """
+    Pretty print an object in a box.
+    """
+    rich.print(
+        Panel(Pretty(obj, expand_all=True), title=title, border_style=border_style)
+    )
+
+
 def console_rule(msg, do_norm_msg=True, is_end_tag=False):
     msg = norm_str(msg) if do_norm_msg else msg
     if is_end_tag:

halib-0.1.48/halib/research/benchquery.py

@@ -0,0 +1,131 @@
+import pandas as pd
+from rich.pretty import pprint
+from argparse import ArgumentParser
+
+def cols_to_col_groups(df):
+    columns = list(df.columns)
+    # pprint(columns)
+
+    col_groups = []
+    current_group = []
+
+    def have_unnamed(col_group):
+        return any("unnamed" in col.lower() for col in col_group)
+
+    for i, col in enumerate(columns):
+        # Add the first column to the current group
+        if not current_group:
+            current_group.append(col)
+            continue
+
+        prev_col = columns[i - 1]
+        # Check if current column is "unnamed" or shares base name with previous
+        # Assuming "equal" means same base name (before any suffix like '_1')
+        base_prev = (
+            prev_col.split("_")[0].lower() if "_" in prev_col else prev_col.lower()
+        )
+        base_col = col.split("_")[0].lower() if "_" in col else col.lower()
+        is_unnamed = "unnamed" in col.lower()
+        is_equal = base_col == base_prev
+
+        if is_unnamed or is_equal:
+            # Add to current group
+            current_group.append(col)
+        else:
+            # Start a new group
+            col_groups.append(current_group)
+            current_group = [col]
+    # Append the last group
+    if current_group:
+        col_groups.append(current_group)
+    meta_dict = {"common_cols": [], "db_cols": []}
+    for group in col_groups:
+        if not have_unnamed(group):
+            meta_dict["common_cols"].extend(group)
+        else:
+            # find the first unnamed column
+            named_col = next(
+                (col for col in group if "unnamed" not in col.lower()), None
+            )
+            group_cols = [f"{named_col}_{i}" for i in range(len(group))]
+            meta_dict["db_cols"].extend(group_cols)
+    return meta_dict
+
+# def bech_by_db_name(df, db_list="db1, db2", key_metrics="p, r, f1, acc"):
+
+
+def str_2_list(input_str, sep=","):
+    out_ls = []
+    if len(input_str.strip()) == 0:
+        return out_ls
+    if sep not in input_str:
+        out_ls.append(input_str.strip())
+        return out_ls
+    else:
+        out_ls = [item.strip() for item in input_str.split(sep) if item.strip()]
+        return out_ls
+
+
+def filter_bech_df_by_db_and_metrics(df, db_list="", key_metrics=""):
+    meta_cols_dict = cols_to_col_groups(df)
+    op_df = df.copy()
+    op_df.columns = (
+        meta_cols_dict["common_cols"].copy() + meta_cols_dict["db_cols"].copy()
+    )
+    filterd_cols = []
+    filterd_cols.extend(meta_cols_dict["common_cols"])
+
+    selected_db_list = str_2_list(db_list)
+    db_filted_cols = []
+    if len(selected_db_list) > 0:
+        for db_name in db_list.split(","):
+            db_name = db_name.strip()
+            for col_name in meta_cols_dict["db_cols"]:
+                if db_name.lower() in col_name.lower():
+                    db_filted_cols.append(col_name)
+    else:
+        db_filted_cols = meta_cols_dict["db_cols"]
+
+    filterd_cols.extend(db_filted_cols)
+    df_filtered = op_df[filterd_cols].copy()
+    df_filtered
+
+    selected_metrics_ls = str_2_list(key_metrics)
+    if len(selected_metrics_ls) > 0:
+        # get the second row as metrics row (header)
+        metrics_row = df_filtered.iloc[0].copy()
+        # only get the values in columns in (db_filterd_cols)
+        metrics_values = metrics_row[db_filted_cols].values
+        keep_metrics_cols = []
+        # create a zip of db_filted_cols and metrics_values (in that metrics_row)
+        metrics_list = list(zip(metrics_values, db_filted_cols))
+        selected_metrics_ls = [metric.strip().lower() for metric in selected_metrics_ls]
+        for metric, col_name in metrics_list:
+            if metric.lower() in selected_metrics_ls:
+                keep_metrics_cols.append(col_name)
+
+    else:
+        pprint("No metrics selected, keeping all db columns")
+        keep_metrics_cols = db_filted_cols
+
+    final_filterd_cols = meta_cols_dict["common_cols"].copy() + keep_metrics_cols
+    df_final = df_filtered[final_filterd_cols].copy()
+    return df_final
+
+
+def parse_args():
+    parser = ArgumentParser(
+        description="desc text")
+    parser.add_argument('-csv', '--csv', type=str, help='CSV file path', default=r"E:\Dev\__halib\test\bench.csv")
+    return parser.parse_args()
+
+
+def main():
+    args = parse_args()
+    csv_file = args.csv
+    df = pd.read_csv(csv_file, sep=";", encoding="utf-8")
+    filtered_df = filter_bech_df_by_db_and_metrics(df, "bowfire", "acc")
+    print(filtered_df)
+
+if __name__ == "__main__":
+    main()

{halib-0.1.46/halib → halib-0.1.48/halib/research}/plot.py

@@ -1,6 +1,6 @@
-from .common import now_str, norm_str, ConsoleLog
-from .filetype import csvfile
-from .system import filesys as fs
+from ..common import now_str, norm_str, ConsoleLog
+from ..filetype import csvfile
+from ..system import filesys as fs
 from functools import partial
 from rich.console import Console
 from rich.pretty import pprint

{halib-0.1.46/halib → halib-0.1.48/halib/research}/torchloader.py

@@ -6,9 +6,9 @@
  * @desc this module works as a utility tools for finding the best configuration for dataloader (num_workers, batch_size, pin_menory, etc.) that fits your hardware.
 """
 from argparse import ArgumentParser
-from .common import *
-from .filetype import csvfile
-from .filetype.yamlfile import load_yaml
+from ..common import *
+from ..filetype import csvfile
+from ..filetype.yamlfile import load_yaml
 from rich import inspect
 from torch.utils.data import DataLoader
 from torchvision import datasets, transforms

{halib-0.1.46/halib → halib-0.1.48/halib/utils}/tele_noti.py

@@ -10,8 +10,8 @@ from rich.pretty import pprint
 from rich.console import Console
 import plotly.graph_objects as go
 
-from .system import filesys as fs
-from .filetype import textfile, csvfile
+from ..system import filesys as fs
+from ..filetype import textfile, csvfile
 
 from argparse import ArgumentParser
 

{halib-0.1.46 → halib-0.1.48/halib.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: halib
-Version: 0.1.46
+Version: 0.1.48
 Summary: Small library for common tasks
 Author: Hoang Van Ha
 Author-email: hoangvanhauit@gmail.com
@@ -15,6 +15,13 @@ License-File: LICENSE.txt
 
 Helper package for coding and automation
 
+**Version 0.1.48**
+
++ add `research` module to help with research tasks, including `benchquery` for benchmarking queries from dataframe
+
+**Version 0.1.47**
++ add `pprint_box` to print object/string in a box frame (like in `inspect`)
+
 **Version 0.1.46**
 + filter the warning message of `UserWarning: Unable to import Axes3D.`
 + auto_wrap_text for `fn_display_df` to avoid long text in the table

{halib-0.1.46 → halib-0.1.48}/halib.egg-info/SOURCES.txt

@@ -7,12 +7,7 @@ setup.py
 halib/__init__.py
 halib/common.py
 halib/cuda.py
-halib/dataset.py
-halib/listop.py
-halib/plot.py
 halib/rich_color.py
-halib/tele_noti.py
-halib/torchloader.py
 halib.egg-info/PKG-INFO
 halib.egg-info/SOURCES.txt
 halib.egg-info/dependency_links.txt
@@ -29,8 +24,16 @@ halib/online/gdrive.py
 halib/online/gdrive_mkdir.py
 halib/online/gdrive_test.py
 halib/online/projectmake.py
+halib/research/__init__.py
+halib/research/benchquery.py
+halib/research/dataset.py
+halib/research/plot.py
+halib/research/torchloader.py
 halib/system/__init__.py
 halib/system/cmd.py
 halib/system/filesys.py
+halib/utils/__init__.py
+halib/utils/listop.py
+halib/utils/tele_noti.py
 test/test15.py
 test/test_df_creator.py

{halib-0.1.46 → halib-0.1.48}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt") as f:
 
 setuptools.setup(
     name="halib",
-    version="0.1.46",
+    version="0.1.48",
     author="Hoang Van Ha",
     author_email="hoangvanhauit@gmail.com",
     description="Small library for common tasks",