Skip to content

Data API

DataLoader

Fetch and preprocess financial data from Yahoo Finance.

Parameters:

Name Type Description Default
tickers list of str

List of ticker symbols to fetch

 required
start_date str or datetime

Start date for historical data (YYYY-MM-DD format)

 required
end_date str or datetime

End date for historical data (YYYY-MM-DD format)

 required

Examples:

>>> loader = DataLoader(['VTI', 'BND'], '2020-01-01', '2023-12-31')
>>> data = loader.fetch_data()
Source code in portfolio_analysis/data/loader.py 
 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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
class DataLoader:
    """
    Fetch and preprocess financial data from Yahoo Finance.

    Parameters
    ----------
    tickers : list of str
        List of ticker symbols to fetch
    start_date : str or datetime
        Start date for historical data (YYYY-MM-DD format)
    end_date : str or datetime
        End date for historical data (YYYY-MM-DD format)

    Examples
    --------
    >>> loader = DataLoader(['VTI', 'BND'], '2020-01-01', '2023-12-31')
    >>> data = loader.fetch_data()
    """

    def __init__(
        self,
        tickers: list[str],
        start_date: Union[str, datetime],
        end_date: Union[str, datetime],
    ):
        self.tickers = tickers
        self.start_date = start_date
        self.end_date = end_date

    def fetch_data(self, progress: bool = True) -> pd.DataFrame:
        """
        Fetch adjusted close prices for all tickers.

        Parameters
        ----------
        progress : bool, default True
            Show download progress bar

        Returns
        -------
        pd.DataFrame
            DataFrame with dates as index and tickers as columns
        """
        raw_data = yf.download(
            self.tickers, start=self.start_date, end=self.end_date, progress=progress
        )

        # Handle yfinance column format changes across versions
        # yfinance >= 0.2.40: 'Close' is adjusted, MultiIndex is (Price, Ticker)
        # yfinance < 0.2.40: 'Adj Close' exists, MultiIndex is (Price, Ticker)
        if isinstance(raw_data.columns, pd.MultiIndex):
            # Multi-ticker download with MultiIndex columns
            price_types = raw_data.columns.get_level_values(0).unique()
            if "Adj Close" in price_types:
                data = raw_data["Adj Close"]
            elif "Close" in price_types:
                data = raw_data["Close"]
            else:
                raise ValueError(
                    f"No Close or Adj Close column found. Available: {price_types.tolist()}"
                )
        else:
            # Single ticker or flat columns
            if "Adj Close" in raw_data.columns:
                data = raw_data["Adj Close"]
            elif "Close" in raw_data.columns:
                data = raw_data["Close"]
            else:
                raise ValueError(
                    f"No Close or Adj Close column found. Available: {raw_data.columns.tolist()}"
                )

        # Handle single ticker case - ensure DataFrame format
        if isinstance(data, pd.Series):
            data = data.to_frame(name=self.tickers[0])

        return data

    def fetch_returns(
        self, frequency: str = "daily", progress: bool = True
    ) -> pd.DataFrame:
        """
        Fetch and calculate returns.

        Parameters
        ----------
        frequency : str, default 'daily'
            Return frequency: 'daily', 'weekly', or 'monthly'
        progress : bool, default True
            Show download progress bar

        Returns
        -------
        pd.DataFrame
            DataFrame of returns
        """
        data = self.fetch_data(progress=progress)

        if frequency == "daily":
            returns = data.pct_change().dropna()
        elif frequency == "weekly":
            returns = data.resample("W").last().pct_change().dropna()
        elif frequency == "monthly":
            returns = data.resample("M").last().pct_change().dropna()
        else:
            raise ValueError(f"Unknown frequency: {frequency}")

        return returns

    @staticmethod
    def get_ticker_info(ticker: str) -> dict:
        """
        Get information about a ticker.

        Parameters
        ----------
        ticker : str
            Ticker symbol

        Returns
        -------
        dict
            Ticker information from Yahoo Finance
        """
        return yf.Ticker(ticker).info

fetch_data(progress=True)

Fetch adjusted close prices for all tickers.

Parameters:

Name Type Description Default
progress bool

Show download progress bar

 True

Returns:

Type Description
DataFrame

DataFrame with dates as index and tickers as columns
Source code in portfolio_analysis/data/loader.py 
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
def fetch_data(self, progress: bool = True) -> pd.DataFrame:
    """
    Fetch adjusted close prices for all tickers.

    Parameters
    ----------
    progress : bool, default True
        Show download progress bar

    Returns
    -------
    pd.DataFrame
        DataFrame with dates as index and tickers as columns
    """
    raw_data = yf.download(
        self.tickers, start=self.start_date, end=self.end_date, progress=progress
    )

    # Handle yfinance column format changes across versions
    # yfinance >= 0.2.40: 'Close' is adjusted, MultiIndex is (Price, Ticker)
    # yfinance < 0.2.40: 'Adj Close' exists, MultiIndex is (Price, Ticker)
    if isinstance(raw_data.columns, pd.MultiIndex):
        # Multi-ticker download with MultiIndex columns
        price_types = raw_data.columns.get_level_values(0).unique()
        if "Adj Close" in price_types:
            data = raw_data["Adj Close"]
        elif "Close" in price_types:
            data = raw_data["Close"]
        else:
            raise ValueError(
                f"No Close or Adj Close column found. Available: {price_types.tolist()}"
            )
    else:
        # Single ticker or flat columns
        if "Adj Close" in raw_data.columns:
            data = raw_data["Adj Close"]
        elif "Close" in raw_data.columns:
            data = raw_data["Close"]
        else:
            raise ValueError(
                f"No Close or Adj Close column found. Available: {raw_data.columns.tolist()}"
            )

    # Handle single ticker case - ensure DataFrame format
    if isinstance(data, pd.Series):
        data = data.to_frame(name=self.tickers[0])

    return data

fetch_returns(frequency='daily', progress=True)

Fetch and calculate returns.

Parameters:

Name Type Description Default
frequency str

Return frequency: 'daily', 'weekly', or 'monthly'

 'daily'
progress bool

Show download progress bar

 True

Returns:

Type Description
DataFrame

DataFrame of returns
Source code in portfolio_analysis/data/loader.py 
 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
118
119
def fetch_returns(
    self, frequency: str = "daily", progress: bool = True
) -> pd.DataFrame:
    """
    Fetch and calculate returns.

    Parameters
    ----------
    frequency : str, default 'daily'
        Return frequency: 'daily', 'weekly', or 'monthly'
    progress : bool, default True
        Show download progress bar

    Returns
    -------
    pd.DataFrame
        DataFrame of returns
    """
    data = self.fetch_data(progress=progress)

    if frequency == "daily":
        returns = data.pct_change().dropna()
    elif frequency == "weekly":
        returns = data.resample("W").last().pct_change().dropna()
    elif frequency == "monthly":
        returns = data.resample("M").last().pct_change().dropna()
    else:
        raise ValueError(f"Unknown frequency: {frequency}")

    return returns

get_ticker_info(ticker) staticmethod

Get information about a ticker.

Parameters:

Name Type Description Default
ticker str

Ticker symbol

 required

Returns:

Type Description
dict

Ticker information from Yahoo Finance
Source code in portfolio_analysis/data/loader.py 
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
@staticmethod
def get_ticker_info(ticker: str) -> dict:
    """
    Get information about a ticker.

    Parameters
    ----------
    ticker : str
        Ticker symbol

    Returns
    -------
    dict
        Ticker information from Yahoo Finance
    """
    return yf.Ticker(ticker).info