zhenpy 0.1.0__tar.gz

zhenpy-0.1.0/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: zhenpy
+Version: 0.1.0
+Summary: Utility functions for loading and saving data files (CSV, TSV, JSON, JSONL, Excel)
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/lizhen/zhenpy
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+
+# zhenpy
+私人使用的脚本

zhenpy-0.1.0/README.md

@@ -0,0 +1,2 @@
+# zhenpy
+私人使用的脚本

zhenpy-0.1.0/pyproject.toml

@@ -0,0 +1,20 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "zhenpy"
+version = "0.1.0"
+description = "Utility functions for loading and saving data files (CSV, TSV, JSON, JSONL, Excel)"
+readme = "README.md"
+license = "MIT"
+requires-python = ">=3.8"
+dependencies = [
+    "pandas",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/lizhen/zhenpy"
+
+[tool.setuptools.packages.find]
+include = ["utils*"]

zhenpy-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

zhenpy-0.1.0/utils/__init__.py

@@ -0,0 +1,12 @@
+from utils.load import load_jsonl, load_jsonl_dataframe, load_json_dataframe, load_file_dataframe
+from utils.save import save_jsonl, save_json, save_dataframe
+
+__all__ = [
+    "load_jsonl",
+    "load_jsonl_dataframe",
+    "load_json_dataframe",
+    "load_file_dataframe",
+    "save_jsonl",
+    "save_json",
+    "save_dataframe",
+]

zhenpy-0.1.0/utils/load.py

@@ -0,0 +1,51 @@
+import pandas as pd
+import json
+from pandas import DataFrame
+
+
+def load_jsonl(input_file, names=None) -> DataFrame:
+    if 'csv' in input_file:
+        return pd.read_csv(input_file, names=names) if names else pd.read_csv(input_file)
+    if 'tsv' in input_file:
+        return pd.read_csv(input_file, sep='\t', names=names) if names else pd.read_csv(input_file, sep='\t')
+
+    datas = []
+    with open(input_file, "r", encoding="utf8") as reader:
+        for line in reader:
+            line = line.strip() 
+            json_line = json.loads(line)
+            datas.append(json_line)
+
+    return DataFrame(datas)
+
+
+def load_jsonl_dataframe(input_file):
+    datas = []
+    with open(input_file, "r", encoding="utf8") as reader:
+        for line in reader:
+            line = line.strip() 
+            json_line = json.loads(line)
+            datas.append(json_line)
+    return DataFrame(datas)
+
+def load_json_dataframe(input_file):
+    datas = []
+    with open(input_file, encoding='utf8') as f:
+        datas = json.load(f)
+    
+    return DataFrame(datas)
+
+def load_file_dataframe(input_file, names=None) -> DataFrame:
+    if 'csv' in input_file:
+        return pd.read_csv(input_file, names=names) if names else pd.read_csv(input_file)
+    elif 'tsv' in input_file:
+        return pd.read_csv(input_file, sep='\t', names=names) if names else pd.read_csv(input_file, sep='\t')
+    elif 'xlsx' in input_file:
+        return pd.read_excel(input_file)
+    elif 'jsonl' in input_file:
+        return load_jsonl_dataframe(input_file)
+    elif 'json' in input_file:
+        return load_json_dataframe(input_file)
+    else:
+        print(f"File :{input_file}, doesn't contains suffix [csv, tsv, jsonl, json]")
+    return None

zhenpy-0.1.0/utils/save.py

@@ -0,0 +1,44 @@
+import json
+from pathlib import Path
+
+import pandas as pd
+
+
+def _get_suffix(file_path: str) -> str:
+    return Path(file_path).suffix.lower()
+
+
+def save_jsonl(df: pd.DataFrame, output_file: str) -> None:
+    """Save DataFrame to JSONL format (one JSON object per line)."""
+    with open(output_file, "w", encoding="utf-8") as f:
+        for record in df.to_dict("records"):
+            f.write(json.dumps(record, ensure_ascii=False) + "\n")
+
+
+def save_json(df: pd.DataFrame, output_file: str) -> None:
+    """Save DataFrame to a single JSON array."""
+    with open(output_file, "w", encoding="utf-8") as f:
+        json.dump(df.to_dict("records"), f, ensure_ascii=False)
+
+
+def save_dataframe(df: pd.DataFrame, output_file: str) -> None:
+    """Save DataFrame to file based on extension.
+
+    Supported formats: csv, tsv, jsonl, json, xlsx.
+    """
+    suffix = _get_suffix(output_file)
+    handlers = {
+        ".csv": lambda: df.to_csv(output_file, index=False),
+        ".tsv": lambda: df.to_csv(output_file, sep="\t", index=False),
+        ".jsonl": lambda: save_jsonl(df, output_file),
+        ".json": lambda: save_json(df, output_file),
+        ".xlsx": lambda: df.to_excel(output_file, index=False),
+    }
+
+    handler = handlers.get(suffix)
+    if handler is None:
+        raise ValueError(
+            f"Unsupported file extension '{suffix}' in '{output_file}'. "
+            f"Supported: {', '.join(handlers.keys())}"
+        )
+    handler()

zhenpy-0.1.0/zhenpy.egg-info/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: zhenpy
+Version: 0.1.0
+Summary: Utility functions for loading and saving data files (CSV, TSV, JSON, JSONL, Excel)
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/lizhen/zhenpy
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: pandas
+
+# zhenpy
+私人使用的脚本

zhenpy-0.1.0/zhenpy.egg-info/SOURCES.txt

@@ -0,0 +1,10 @@
+README.md
+pyproject.toml
+utils/__init__.py
+utils/load.py
+utils/save.py
+zhenpy.egg-info/PKG-INFO
+zhenpy.egg-info/SOURCES.txt
+zhenpy.egg-info/dependency_links.txt
+zhenpy.egg-info/requires.txt
+zhenpy.egg-info/top_level.txt

zhenpy-0.1.0/zhenpy.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

zhenpy-0.1.0/zhenpy.egg-info/requires.txt

@@ -0,0 +1 @@
+pandas

zhenpy-0.1.0/zhenpy.egg-info/top_level.txt

@@ -0,0 +1 @@
+utils