import pandas as pd
import numpy as np
from src.data import data_collection, data_preprocessing

def test_collect_data():
    url = "https://github.com/plotly/datasets/raw/master/tesla-stock-price.csv"
    data = data_collection.collect_data(url)

    assert isinstance(data, pd.DataFrame)  # Assert that a DataFrame is returned
    assert data.shape[0] > 0  # Assert that the DataFrame is not empty
    assert set(data.columns) == set(['Date', 'Open', 'High', 'Low', 'Close', 'Volume'])  # Assert the columns are as expected

def test_preprocess_data():
    url = "https://github.com/plotly/datasets/raw/master/tesla-stock-price.csv"
    raw_data = data_collection.collect_data(url)
    processed_data = data_preprocessing.preprocess_data(raw_data)

    assert isinstance(processed_data, pd.DataFrame)
    assert processed_data.shape[0] > 0  # Assert that the dataframe is not empty
    # Assert that the processed data columns are as expected
    assert set(processed_data.columns) == set(['Processed_Open', 'Processed_High', 'Processed_Low', 'Processed_Close', 'Processed_Volume'])
    assert pd.api.types.is_numeric_dtype(processed_data["Processed_Open"])  # Assert that the 'Processed_Open' column is numeric
    assert pd.api.types.is_numeric_dtype(processed_data["Processed_High"])  # Assert that the 'Processed_High' column is numeric
    assert pd.api.types.is_numeric_dtype(processed_data["Processed_Low"])  # Assert that the 'Processed_Low' column is numeric
    assert pd.api.types.is_numeric_dtype(processed_data["Processed_Close"])  # Assert that the 'Processed_Close' column is numeric
    assert pd.api.types.is_numeric_dtype(processed_data["Processed_Volume"])  # Assert that the 'Processed_Volume' column is numeric

if __name__ == "__main__":
    test_collect_data()
    test_preprocess_data()