Upload pandas/Test_Pandas.py with huggingface_hub

pandas/Test_Pandas.py

@@ -0,0 +1,282 @@
+"""
+Generated by RIMI
+"""
+import sys
+import traceback
+
+passed = 0
+failed = 0
+skipped = 0
+
+def test(name, func):
+    global passed, failed, skipped
+    try:
+        result = func()
+        if isinstance(result, str) and result == "SKIP":
+            skipped += 1
+            print(f"  SKIP  #{passed+failed+skipped:02d} {name}")
+        else:
+            passed += 1
+            print(f"  OK    #{passed+failed+skipped:02d} {name}")
+    except Exception as e:
+        failed += 1
+        print(f"  FAIL  #{passed+failed+skipped:02d} {name}: {e}")
+        traceback.print_exc()
+
+print("=" * 60)
+print("pandas 2.3.3 — Android norelro test")
+print("Python", sys.version)
+print("=" * 60)
+
+# 1. import pandas
+test("import pandas", lambda: __import__("pandas"))
+
+# 2. version check
+test("pandas.__version__", lambda: None if __import__("pandas").__version__ == "2.3.3" else (_ for _ in ()).throw(Exception(f"wrong version")))
+
+# 3. import numpy (bundled dep)
+test("import numpy (bundled dep)", lambda: __import__("numpy"))
+
+# 4. DataFrame basics
+test("DataFrame create", lambda: __import__("pandas").DataFrame({"a": [1, 2], "b": [3, 4]}))
+
+# 5. DataFrame shape
+def test_shape():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
+    assert df.shape == (3, 2), f"wrong shape: {df.shape}"
+test("DataFrame shape", test_shape)
+
+# 6. DataFrame head/tail
+def test_head_tail():
+    import pandas as pd
+    df = pd.DataFrame({"x": range(100)})
+    assert len(df.head(5)) == 5
+    assert len(df.tail(5)) == 5
+test("DataFrame head/tail", test_head_tail)
+
+# 7. DataFrame dtypes
+def test_dtypes():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2], "b": [1.0, 2.0], "c": ["x", "y"]})
+    assert df.dtypes["a"].name == "int64"
+    assert df.dtypes["b"].name == "float64"
+    assert df.dtypes["c"].name == "object"
+test("DataFrame dtypes", test_dtypes)
+
+# 8. DataFrame describe
+def test_describe():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2, 3, 4, 5]})
+    desc = df.describe()
+    assert desc.loc["mean", "a"] == 3.0
+test("DataFrame describe", test_describe)
+
+# 9. DataFrame groupby
+def test_groupby():
+    import pandas as pd
+    df = pd.DataFrame({"g": ["a", "a", "b"], "v": [1, 2, 3]})
+    result = df.groupby("g")["v"].sum()
+    assert result["a"] == 3
+    assert result["b"] == 3
+test("DataFrame groupby", test_groupby)
+
+# 10. DataFrame sort
+def test_sort():
+    import pandas as pd
+    df = pd.DataFrame({"a": [3, 1, 2]})
+    df_sorted = df.sort_values("a")
+    assert list(df_sorted["a"]) == [1, 2, 3]
+test("DataFrame sort_values", test_sort)
+
+# 11. DataFrame apply
+def test_apply():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2, 3]})
+    result = df["a"].apply(lambda x: x * 2)
+    assert list(result) == [2, 4, 6]
+test("DataFrame apply", test_apply)
+
+# 12. DataFrame merge
+def test_merge():
+    import pandas as pd
+    a = pd.DataFrame({"k": [1, 2], "v": ["a", "b"]})
+    b = pd.DataFrame({"k": [1, 2], "w": ["c", "d"]})
+    m = a.merge(b, on="k")
+    assert list(m.columns) == ["k", "v", "w"]
+    assert len(m) == 2
+test("DataFrame merge", test_merge)
+
+# 13. DataFrame concat
+def test_concat():
+    import pandas as pd
+    a = pd.DataFrame({"a": [1, 2]})
+    b = pd.DataFrame({"a": [3, 4]})
+    c = pd.concat([a, b], ignore_index=True)
+    assert list(c["a"]) == [1, 2, 3, 4]
+test("DataFrame concat", test_concat)
+
+# 14. DataFrame fillna/dropna
+def test_fillna():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, None, 3]})
+    filled = df.fillna(0)
+    assert list(filled["a"]) == [1.0, 0.0, 3.0]
+    dropped = df.dropna()
+    assert len(dropped) == 2
+test("DataFrame fillna/dropna", test_fillna)
+
+# 15. DataFrame pivot
+def test_pivot():
+    import pandas as pd
+    df = pd.DataFrame({"r": ["a", "a"], "c": ["x", "y"], "v": [1, 2]})
+    p = df.pivot(index="r", columns="c", values="v")
+    assert p.loc["a", "x"] == 1
+    assert p.loc["a", "y"] == 2
+test("DataFrame pivot", test_pivot)
+
+# 16. DataFrame melt
+def test_melt():
+    import pandas as pd
+    df = pd.DataFrame({"id": [1], "x": [2], "y": [3]})
+    m = pd.melt(df, id_vars=["id"])
+    assert len(m) == 2
+test("DataFrame melt", test_melt)
+
+# 17. Series operations
+def test_series():
+    import pandas as pd
+    s = pd.Series([1, 2, 3, 4])
+    assert s.sum() == 10
+    assert s.mean() == 2.5
+    assert s.max() == 4
+    assert s.min() == 1
+test("Series agg ops", test_series)
+
+# 18. DatetimeIndex
+def test_datetime():
+    import pandas as pd
+    dates = pd.date_range("2024-01-01", periods=5, freq="D")
+    assert len(dates) == 5
+    assert dates[0].year == 2024
+    assert dates[0].month == 1
+    assert dates[0].day == 1
+test("DatetimeIndex", test_datetime)
+
+# 19. Timedelta
+def test_timedelta():
+    import pandas as pd
+    td = pd.Timedelta("1 day 2 hours")
+    assert td.total_seconds() == 93600.0
+test("Timedelta", test_timedelta)
+
+# 20. read_csv / to_csv roundtrip
+def test_csv():
+    import pandas as pd, os, tempfile
+    df = pd.DataFrame({"a": [1, 2, 3], "b": ["x", "y", "z"]})
+    with tempfile.NamedTemporaryFile(suffix=".csv", delete=False, mode="w") as f:
+        df.to_csv(f, index=False)
+        tmp = f.name
+    df2 = pd.read_csv(tmp)
+    os.unlink(tmp)
+    assert list(df2["a"]) == [1, 2, 3]
+    assert list(df2["b"]) == ["x", "y", "z"]
+test("read_csv / to_csv roundtrip", test_csv)
+
+# 21. read_json / to_json roundtrip
+def test_json():
+    import pandas as pd, os, tempfile
+    df = pd.DataFrame({"a": [1, 2], "b": [3.0, 4.0]})
+    with tempfile.NamedTemporaryFile(suffix=".json", delete=False) as f:
+        df.to_json(f, orient="records")
+        tmp = f.name
+    df2 = pd.read_json(tmp, orient="records")
+    os.unlink(tmp)
+    assert list(df2["a"]) == [1, 2]
+test("read_json / to_json roundtrip", test_json)
+
+# 22. DataFrame value_counts
+def test_value_counts():
+    import pandas as pd
+    s = pd.Series(["a", "b", "a", "a", "b"])
+    vc = s.value_counts()
+    assert vc["a"] == 3
+    assert vc["b"] == 2
+test("Series value_counts", test_value_counts)
+
+# 23. DataFrame corr
+def test_corr():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2, 3], "b": [2, 4, 6]})
+    corr = df["a"].corr(df["b"])
+    assert abs(corr - 1.0) < 1e-10
+test("DataFrame corr", test_corr)
+
+# 24. DataFrame map/replace
+def test_replace():
+    import pandas as pd
+    s = pd.Series([1, 2, 3])
+    r = s.replace({1: "a", 2: "b", 3: "c"})
+    assert list(r) == ["a", "b", "c"]
+test("Series replace", test_replace)
+
+# 25. MultiIndex
+def test_multiindex():
+    import pandas as pd
+    arrays = [["a", "a", "b", "b"], [1, 2, 1, 2]]
+    idx = pd.MultiIndex.from_arrays(arrays, names=["l1", "l2"])
+    df = pd.DataFrame({"v": [10, 20, 30, 40]}, index=idx)
+    assert df.loc["a", 1].iloc[0] == 10
+test("MultiIndex", test_multiindex)
+
+# 26. DataFrame to_numpy
+def test_to_numpy():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
+    arr = df.to_numpy()
+    assert arr.shape == (2, 2)
+    assert arr[0, 0] == 1
+    assert arr[1, 1] == 4
+test("DataFrame to_numpy", test_to_numpy)
+
+# 27. Categorical
+def test_categorical():
+    import pandas as pd
+    s = pd.Categorical(["a", "b", "a", "c"])
+    assert len(s) == 4
+    assert s.categories.tolist() == ["a", "b", "c"]
+test("Categorical", test_categorical)
+
+# 28. DataFrame assign
+def test_assign():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2]})
+    df2 = df.assign(b=df["a"] * 10)
+    assert list(df2["b"]) == [10, 20]
+test("DataFrame assign", test_assign)
+
+# 29. DataFrame pipe
+def test_pipe():
+    import pandas as pd
+    df = pd.DataFrame({"a": [1, 2, 3]})
+    def add_one(data):
+        return data.assign(b=data["a"] + 1)
+    df2 = df.pipe(add_one)
+    assert list(df2["b"]) == [2, 3, 4]
+test("DataFrame pipe", test_pipe)
+
+# 30. DataFrame nunique/nlargest
+def test_nlargest():
+    import pandas as pd
+    df = pd.DataFrame({"a": [10, 1, 5, 20, 3]})
+    top = df.nlargest(2, "a")
+    assert list(top["a"]) == [20, 10]
+test("DataFrame nlargest", test_nlargest)
+
+print()
+print("=" * 60)
+print(f"RESULT: {passed} PASS, {failed} FAIL, {skipped} SKIP")
+print("=" * 60)
+
+if failed > 0:
+    sys.exit(1)