File size: 3,982 Bytes
f5407b6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
# Import the necessary libraries
import os
import json
import pytest
import pandas as pd
from dynamicts.data_loader import DataLoader
from dynamicts.analysis import UnivariateAnalysis
# Dummy test cases
def test_null():
assert True
# Constants
data_url = "https://raw.githubusercontent.com/Chinar-Quantum-AI-Ltd/public_datasets/main/bitcoin_price.csv"
loader = DataLoader(filepath=data_url, index_col="Date")
# tEST FOR DATA loader
def test_load_success():
df = loader.load()
# check datframe loaded
assert isinstance(df, pd.DataFrame)
# columns are lower case
assert all(col == col.lower() for col in df.columns)
# index is lower case
assert df.index.name == "date"
def test_load_failure():
url = "https://raw.githubusercontent.com/Chinar-Quantum-AI-Ltd/public_datasets/main/price.csv" # invalid url for testing
loader = DataLoader(
filepath=url, index_col="Date"
)
with pytest.raises(ValueError):
loader.load()
def test_is_regular():
# loader = DataLoader(
# filepath=data_url,
# index_col="Date"
# )
loader.load()
assert loader.is_regular() is True
def test_is_regular_false(tmp_path):
# Create irregular CSV
irregular = tmp_path / "irregular.csv"
# create dummy irregular data
dts = pd.to_datetime(["2021-01-01", "2021-01-02", "2021-01-04", "2021-01-07"])
df_irreg = pd.DataFrame({"date": dts, "y": [1,2,3,4]}).set_index("date")
df_irreg.to_csv(irregular)
loader = DataLoader(filepath=str(irregular), index_col="date")
loader.load()
assert loader.is_regular() is False
def test_save_metadata(tmp_path, monkeypatch):
# Monkey patch workingh dir to temp path for clean metadata
monkeypatch.chdir(tmp_path)
# loader = DataLoader(
# filepath=data_url,
# index_col="Date"
# )
df = loader.load()
# Save metadata (writes to ./metadata/<filename>_meta.json)
loader.save_metadata()
# Verify expected file exists
expected_filename = os.path.splitext(os.path.basename(data_url))[0] + "_meta.json"
meta_path = tmp_path / "metadata" / expected_filename
assert meta_path.exists()
# Check metadata content
with open(meta_path) as f:
meta = json.load(f)
assert meta["columns"] == list(df.columns)
assert meta["shape"] == list(df.shape) or tuple(df.shape)
assert meta["index_name"] == df.index.name
# # Some Test cases for analysis.py script
# # Tests for univariate analysis module
# def test_ditribution_stats_and_missing(monkeypatch, tmp_path):
# analysis = UnivariateAnalysis(
# filepath=data_url,
# target_col="Close",
# index_col="Date"
# )
# # test distribution stats
# stats = analysis.check_distribution_stats()
# assert "skewness" in stats
# assert "kurtosis" in stats
# assert isinstance(stats["skewness"], float)
# assert isinstance(stats["kurtosis"], float)
# # # test missing values
# # missing = analysis.check_missing_values()
# # assert "missing_count" in missing
# # assert "missing_percentage" in missing
# # assert isinstance(missing["missing_percentage"], float)
# def test_outlier_detection_and_rolling():
# analysis = UnivariateAnalysis(
# filepath=data_url,
# target_col="Close",
# index_col="Date"
# )
# # tests for outlier detection
# outliers = analysis.detect_outliers(method="both", plot=False)
# assert "outliers_detected" in outliers
# assert outliers["outliers_detected"] >= 0
# # test for rolling stat
# rolling = analysis.measure_rolling_statistics(window=7)
# assert "rolling_mean" in rolling
# assert isinstance(rolling["rolling_mean"], pd.Series)
# assert rolling["rolling_mean"].shape == analysis.df["close"].shape |