Upload pandas/PANDAS_USER_GUIDE.txt with huggingface_hub

pandas/PANDAS_USER_GUIDE.txt

@@ -0,0 +1,142 @@
+pandas — USER GUIDE (Android Python STB)
+=========================================
+Generated by RIMI
+Version: pandas 2.3.3
+Python: 3.12.14
+
+WHAT IS PANDAS?
+---------------
+pandas is the most popular Python library for data analysis and manipulation.
+It provides fast, expressive DataFrames (tabular data) and Series (1D data)
+that make working with structured data easy and intuitive.
+
+In PythonSTB, pandas is used for:
+  - EPG (Electronic Program Guide) data parsing and querying
+  - Channel list management and filtering
+  - Playlist data transformation
+  - Analytics and statistics
+  - CSV/JSON data processing
+
+QUICK START
+-----------
+import pandas as pd
+
+# Create a DataFrame
+df = pd.DataFrame({
+    "channel": ["BBC One", "CNN", "Sky News"],
+    "category": ["entertainment", "news", "news"],
+    "rating": [4.5, 4.2, 4.0]
+})
+
+# Filter
+news = df[df["category"] == "news"]
+
+# Sort
+top = df.sort_values("rating", ascending=False)
+
+# Save / Load
+df.to_csv("channels.csv", index=False)
+df = pd.read_csv("channels.csv")
+
+CORE CONCEPTS
+-------------
+1. DataFrame: 2D table (like a spreadsheet or SQL table)
+   df = pd.DataFrame({"col1": [1,2,3], "col2": ["a","b","c"]})
+
+2. Series: 1D column or row
+   s = df["col1"]
+
+3. Indexing:
+   df.loc[row_label, col_label]     # label-based
+   df.iloc[row_int, col_int]        # position-based
+   df[df["col"] > value]            # boolean mask
+
+4. GroupBy:
+   df.groupby("category")["rating"].mean()
+
+5. Merge/Join:
+   pd.merge(df1, df2, on="key")
+
+COMMON OPERATIONS
+-----------------
+# Filtering
+df[df["rating"] > 4.0]
+df.query("rating > 4.0")
+df.nlargest(5, "rating")
+
+# Aggregation
+df.groupby("category").agg({"rating": "mean", "channel": "count"})
+
+# Transform
+df["normalized"] = (df["rating"] - df["rating"].min()) / (df["rating"].max() - df["rating"].min())
+
+# Pivot
+pd.pivot_table(df, values="rating", index="category", aggfunc="mean")
+
+# Time series
+df["date"] = pd.to_datetime(df["date"])
+df.set_index("date").resample("D").mean()
+
+FILE I/O
+--------
+# CSV
+df.to_csv("data.csv", index=False)
+df = pd.read_csv("data.csv")
+df = pd.read_csv("data.csv", parse_dates=["date"])
+
+# JSON
+df.to_json("data.json", orient="records")
+df = pd.read_json("data.json", orient="records")
+
+# Excel (requires openpyxl)
+df.to_excel("data.xlsx", index=False)
+df = pd.read_excel("data.xlsx")
+
+EPG DATA EXAMPLE
+----------------
+import pandas as pd
+from lxml import etree
+
+def parse_epg(xml_content):
+    root = etree.fromstring(xml_content.encode())
+    rows = []
+    for prog in root.findall(".//programme"):
+        rows.append({
+            "channel": prog.get("channel"),
+            "start": pd.to_datetime(prog.get("start"), format="%Y%m%d%H%M%S %z"),
+            "stop": pd.to_datetime(prog.get("stop"), format="%Y%m%d%H%M%S %z"),
+            "title": prog.findtext("title", ""),
+        })
+    return pd.DataFrame(rows)
+
+# Query: what's on now?
+now = pd.Timestamp.now(tz="UTC")
+on_now = epg[(epg["start"] <= now) & (epg["stop"] > now)]
+
+# Query: shows longer than 1 hour
+long_shows = epg[(epg["stop"] - epg["start"]) > pd.Timedelta(hours=1)]
+
+TIPS FOR ANDROID
+----------------
+- pandas on Android is compiled with norelro + 16KB page alignment
+- Full wheel bundles numpy — no separate numpy install needed
+- Use zipfile-based installer (pip doesn't work from run-as)
+- pandas + numpy together use ~15MB installed
+- All DataFrame operations work the same as desktop Python
+
+TROUBLESHOOTING
+---------------
+# ImportError: numpy required
+# Make sure pandas wheel with bundled numpy is installed (Full_Wheel)
+
+# Slow performance
+# Use vectorized operations instead of Python loops:
+# BAD:  for i in range(len(df)): df.loc[i, "new"] = df.loc[i, "old"] * 2
+# GOOD: df["new"] = df["old"] * 2
+
+# Memory issues with large datasets
+# Use chunked reading:
+# for chunk in pd.read_csv("big.csv", chunksize=1000):
+#     process(chunk)
+
+Generated by RIMI