jse-tools 0.2.1__tar.gz

jse_tools-0.2.1/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: jse-tools
+Version: 0.2.1
+Summary: Utilities for downloading and processing JSE stock data
+Author: Francois Helmie
+Requires-Python: >=3.9
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: requests
+Requires-Dist: yfinance
+Requires-Dist: scipy

jse_tools-0.2.1/jse_tools/__init__.py

@@ -0,0 +1,16 @@
+
+from .core import (
+    get_tickers,
+    safe_request,
+    verify_dataset_integrity,
+    download_and_process,
+    save_tickers
+)
+
+__all__ = [
+    "get_tickers",
+    "safe_request",
+    "verify_dataset_integrity",
+    "download_and_process",
+    "save_tickers"
+]

jse_tools-0.2.1/jse_tools/core.py

@@ -0,0 +1,137 @@
+
+import os
+import time
+import requests
+import pandas as pd
+import yfinance as yf
+import numpy as np
+from scipy import stats
+
+
+# ================================
+# Resilience Layer
+# ================================
+
+def safe_request(url, retries=3, delay=2):
+    """
+    Network resilience wrapper.
+    Retries API call on failure.
+    """
+
+    last_error = None
+
+    for _ in range(retries):
+        try:
+            response = requests.get(url, timeout=10)
+            if response.status_code == 200:
+                return response
+        except requests.exceptions.RequestException as e:
+            last_error = e
+
+        time.sleep(delay)
+
+    raise Exception(f"API request failed after retries. Last error: {last_error}")
+
+
+# ================================
+# Reliability Layer
+# ================================
+
+def verify_dataset_integrity(df, required_columns=None):
+    """
+    Dataset integrity guard.
+
+    Checks:
+    - Dataset not empty
+    - Required columns exist
+    - Missing data ratio threshold
+    """
+
+    if df is None or df.empty:
+        raise ValueError("Dataset integrity failure: DataFrame is empty")
+
+    if required_columns:
+        missing = [c for c in required_columns if c not in df.columns]
+        if missing:
+            raise ValueError(f"Missing required columns: {missing}")
+
+    # Detect pathological missing data
+    null_ratio = df.isna().mean()
+
+    if (null_ratio > 0.5).any():
+        problematic = null_ratio[null_ratio > 0.5].index.tolist()
+        raise ValueError(f"High missing data ratio detected in: {problematic}")
+
+    return True
+
+
+# ================================
+# Main Functions
+# ================================
+
+def get_tickers(api_token):
+    url = f"https://eodhd.com/api/exchange-symbol-list/JSE?api_token={api_token}&fmt=json"
+
+    response = safe_request(url)
+
+    data = response.json()
+
+    if not data:
+        print("Warning: Empty API response")
+        return []
+
+    df = pd.json_normalize(data)
+
+    df = df[df["Code"].str.len() <= 3]
+    df["ticker"] = df["Code"].astype(str) + ".JO"
+
+    return df["ticker"].tolist()
+
+
+def download_and_process(tickers, start_date, end_date, output_dir="Stocks"):
+    os.makedirs(output_dir, exist_ok=True)
+
+    for ticker in tickers:
+        df = yf.download(
+            ticker,
+            start=start_date,
+            end=end_date,
+            auto_adjust=True,
+            progress=False
+        )
+
+        if df is None or df.empty:
+            print(f"Skipping {ticker} (no data)")
+            continue
+
+        df = df[["Open", "High", "Low", "Close", "Volume"]]
+
+        # Reliability check
+        verify_dataset_integrity(
+            df,
+            required_columns=["Open", "High", "Low", "Close", "Volume"]
+        )
+
+        # Outlier removal
+        df = df[(np.abs(stats.zscore(df)) < 3).all(axis=1)]
+
+        df.ffill(inplace=True)
+        df.bfill(inplace=True)
+
+        df.to_csv(os.path.join(output_dir, f"{ticker}.csv"))
+
+    print(f"Saved data in '{output_dir}'")
+
+
+def save_tickers(folder_path):
+
+    tickers = [
+        f[:-4]
+        for f in os.listdir(folder_path)
+        if f.endswith(".csv")
+    ]
+
+    df = pd.DataFrame(tickers, columns=["tickers"])
+    df.to_csv(os.path.join(folder_path, "tickers.csv"), index=False)
+
+    return df

jse_tools-0.2.1/jse_tools.egg-info/PKG-INFO

@@ -0,0 +1,11 @@
+Metadata-Version: 2.4
+Name: jse-tools
+Version: 0.2.1
+Summary: Utilities for downloading and processing JSE stock data
+Author: Francois Helmie
+Requires-Python: >=3.9
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: requests
+Requires-Dist: yfinance
+Requires-Dist: scipy

jse_tools-0.2.1/jse_tools.egg-info/SOURCES.txt

@@ -0,0 +1,8 @@
+pyproject.toml
+jse_tools/__init__.py
+jse_tools/core.py
+jse_tools.egg-info/PKG-INFO
+jse_tools.egg-info/SOURCES.txt
+jse_tools.egg-info/dependency_links.txt
+jse_tools.egg-info/requires.txt
+jse_tools.egg-info/top_level.txt

jse_tools-0.2.1/jse_tools.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

jse_tools-0.2.1/jse_tools.egg-info/requires.txt

@@ -0,0 +1,5 @@
+pandas
+numpy
+requests
+yfinance
+scipy

jse_tools-0.2.1/jse_tools.egg-info/top_level.txt

@@ -0,0 +1 @@
+jse_tools

jse_tools-0.2.1/pyproject.toml

@@ -0,0 +1,20 @@
+
+[build-system]
+requires = ["setuptools>=61"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "jse-tools"
+version = "0.2.1"
+description = "Utilities for downloading and processing JSE stock data"
+authors = [{name = "Francois Helmie"}]
+
+dependencies = [
+    "pandas",
+    "numpy",
+    "requests",
+    "yfinance",
+    "scipy"
+]
+
+requires-python = ">=3.9"

jse_tools-0.2.1/setup.cfg

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