tesorotools-python 0.0.18__py3-none-any.whl

tesorotools/data_sources/lseg.py

@@ -0,0 +1,117 @@
+import time
+from pathlib import Path
+
+import lseg.data as ld
+import pandas as pd
+
+# there should be a better way for testing this
+
+# for the debt stuff we usually use B_YLD_1 as out value
+# for the rest stuff is usually BID
+# sometimes TRD_PRC_1
+# OFF_CLOSE
+
+
+def get_series(
+    api_key: str,
+    series_id_list: list[str],
+    start_date: str,
+    end_date: str,
+    freq: str = "B",
+    fields: list[str] | None = None,
+    cooldown: int = 60,
+    datapoint_limit: int = 2_000,
+    cache_path: Path | None = None,
+) -> pd.DataFrame:
+    """Downloads data from LSEG given that tou have a valid API key"""
+    ld.open_session(app_key=api_key)
+    fields = ["TIMESTAMP", "CLOSE"] if fields is None else fields
+
+    dates_list: list[str] = list(
+        pd.date_range(start=start_date, end=end_date, freq=freq).astype("str")
+    )
+    partial_data: list[pd.DataFrame] = []
+    download_step: int = datapoint_limit // (
+        len(series_id_list) * (len(fields) - 1)
+    )
+    downloaded_dates: int = 0
+    while downloaded_dates < len(dates_list):
+        dates_to_download = dates_list[
+            downloaded_dates : downloaded_dates + download_step
+        ]
+        start = dates_to_download[0]
+        end = dates_to_download[-1]
+        cache_file_path: Path = (
+            cache_path / f"from_{start}_to_{end}.csv"
+            if cache_path is not None
+            else None
+        )
+        if (cache_file_path is None) or (not cache_file_path.exists()):
+            data: pd.DataFrame = block_download(
+                series_id_list,
+                start_date=start,
+                end_date=end,
+                freq=freq,
+                fields=fields,
+                cooldown=cooldown,
+                file_path=cache_file_path,
+            )
+            if cache_file_path is None:
+                partial_data.append(data)
+            if downloaded_dates + download_step < len(dates_list):
+                print(f"Waiting {cooldown} seconds for LSEG to cool down...")
+                time.sleep(cooldown)
+        downloaded_dates += download_step
+    # data = concat_partial_data(cache_path, partial_data)
+    return data
+
+
+def block_download(
+    series_id_list: list[str],
+    start_date: str,
+    end_date: str,
+    freq: str = "B",
+    fields: list[str] | None = None,
+    cooldown: int = 60,
+    file_path: Path | None = None,
+):
+    interval = "daily" if freq == "B" else freq
+
+    while True:
+        try:
+            data: pd.DataFrame | None = ld.get_history(
+                universe=series_id_list,
+                start=start_date,
+                end=end_date,
+                fields=fields,
+                interval=interval,
+            )
+            if data is None:
+                raise ld.errors.LDError(
+                    code=404, message="Service temporarily unavailable"
+                )
+            data = data.drop_duplicates()
+            data = data.sort_index()
+            if len(data.columns) == 1:
+                data.columns = series_id_list
+            if file_path is not None:
+                data.to_csv(file_path)
+            break
+        except ld.errors.LDError as e:
+            print(f"LSEG error: {e}")
+            print("This is probably not our fault")
+        print(f"Waiting {cooldown} seconds for LSEG to cool down...")
+        time.sleep(cooldown)
+    return data
+
+
+def concat_partial_data(
+    cache_path: Path, partial_data: list[pd.DataFrame]
+) -> pd.DataFrame:
+    dfs = partial_data
+    if cache_path is not None:
+        for chunk in cache_path.iterdir():
+            df = pd.read_csv(chunk, index_col="Date")
+            dfs.append(df)
+    full = pd.concat(dfs)
+    return full

tesorotools/database/push.py

@@ -0,0 +1,70 @@
+import json
+
+import pandas as pd
+from sqlalchemy import create_engine
+
+
+def get_connection_string(
+    engine: str,
+    driver: str,
+    username: str,
+    password: str,
+    host: str,
+    database: str,
+) -> str:
+    return f"{engine}+{driver}://{username}:{password}@{host}/{database}"
+
+
+def flash_to_database_format(data: pd.DataFrame) -> pd.DataFrame:
+    """Transform the data in *flash* format to data in *database* format
+
+    This operation takes a little while"""
+
+    data.columns.name = "name"
+    stacked_data = data.stack().to_frame(name="value")
+    database_data = stacked_data.reset_index()
+    database_data["dimensions"] = database_data.apply(
+        lambda row: json.dumps(
+            {
+                "offset": row["offset"],
+                "difference_type": row["difference_type"],
+                "stat": row["stat"],
+            }
+        ),
+        axis=1,
+    )
+    database_data = database_data.drop(
+        columns=["offset", "difference_type", "stat"]
+    )
+    database_data["value_meta"] = pd.NA
+    print(database_data)
+    return database_data
+
+
+def database_to_flash_format():
+    pass
+
+
+def push_to_database(data: pd.DataFrame, conn_string: str, table: str) -> None:
+    engine = create_engine(url=conn_string)
+    data.to_sql(
+        name=table, con=engine, if_exists="append", chunksize=1000, index=False
+    )
+
+
+# this may be just as a datasource (maybe a common protocol?)
+# check the api long video for further reference
+def pull_from_database(
+    conn_string: str, start: str, end: str, series: list[str]
+):
+    # just testing...
+    pd.read_sql_query(
+        """
+        SELECT date, value
+            FROM measurements
+            WHERE
+                date BETWEEN '2007-12-31' AND '2025-04-10' AND name='ES10YT=RR_DIFF' AND
+                dimensions @> '{"offset":"no", "stat":"value"}'
+            ORDER BY date ASC
+        """
+    )

tesorotools/dependencies/functions.py

@@ -0,0 +1,11 @@
+import pandas as pd
+
+
+def difference(
+    target: float | pd.Series, reference: float | pd.Series
+) -> float | pd.Series:
+    return target - reference
+
+
+def inverse(target: float | pd.Series) -> float | pd.Series:
+    return 1 / target

tesorotools/dependencies/node.py

@@ -0,0 +1,34 @@
+from collections.abc import Callable
+from typing import Self
+
+import pandas as pd
+
+from . import functions
+
+
+class Node:
+    def __init__(self, name: str) -> None:
+        self._name: str = name
+        self._edges: list[Self] = []
+
+    def add_edge(self, node: Self) -> None:
+        self._edges.append(node)
+
+    def build_edges(self, *, dependencies: list[str], function: str) -> None:
+        self._resolving_function: Callable[..., float | pd.Series] = getattr(
+            functions, function
+        )
+        for d in dependencies:
+            self.add_edge(Node(d))
+
+    @property
+    def name(self) -> str:
+        return self._name
+
+    @property
+    def edges(self) -> list[Self]:
+        return self._edges
+
+    @property
+    def resolving_function(self) -> Callable[..., float | pd.Series]:
+        return self._resolving_function

tesorotools/dependencies/resolution.py

@@ -0,0 +1,118 @@
+from typing import Any
+
+import pandas as pd
+
+from tesorotools.offsets.offsets import process_raw_data, trim
+
+from .node import Node
+
+
+def resolve(
+    start: Node,
+    resolved: list[Node],
+    unresolved: list[str],
+    independent: set[str],
+    dependencies_cfg: dict[str, Any],
+):
+    if start.name in dependencies_cfg:
+        is_independent: bool = False
+        config: dict[str, Any] = dependencies_cfg[start.name]
+        start.build_edges(**config)
+    else:
+        is_independent: bool = True
+        independent.add(start.name)
+
+    if not is_independent:
+        unresolved.append(start.name)
+        for node in start.edges:
+            if node.name in unresolved:
+                raise ValueError(
+                    f"circular dependency: {start.name} <-> {node.name}"
+                )
+            if node not in resolved:
+                resolve(
+                    node, resolved, unresolved, independent, dependencies_cfg
+                )
+        resolved.append(start)
+        unresolved.remove(start.name)
+
+
+def collect_document_series(
+    config_dicts: list[dict[str, Any]], find: str = "series"
+) -> list[str]:
+    series: set[str] = set()
+    for config_dict in config_dicts:
+        series = series | collect_series(config_dict, find)
+    return list(series)
+
+
+def resolve_series(
+    config_dicts: list[dict[str, Any]], dependencies_cfg: dict[str, Any]
+):
+    series: list[str] = collect_document_series(config_dicts)
+    nodes: list[Node] = [Node(name=name) for name in series]
+    independent_nodes: set[str] = set()
+    resolved: list[Node] = []
+    for node in nodes:
+        resolve(
+            start=node,
+            resolved=resolved,
+            unresolved=[],
+            independent=independent_nodes,
+            dependencies_cfg=dependencies_cfg,
+        )
+
+    return {
+        "independent": independent_nodes,
+        "dependent": resolved,
+    }
+
+
+def compute_derivate_series(
+    dependent_nodes: list[Node], trimmed_data: pd.DataFrame
+):
+    inferred_series: list[pd.Series] = []
+    for node in dependent_nodes:
+        dependencies_names: list[str] = [n.name for n in node.edges]
+        dependencies_df = trimmed_data.loc[:, dependencies_names]
+        dependencies_dict = dependencies_df.to_dict(orient="series").values()
+        inferred: pd.Series = node.resolving_function(*dependencies_dict)
+        inferred.name = node.name
+        inferred_series.append(inferred)
+    inferred_df: pd.DataFrame = pd.concat(inferred_series, axis=1)
+    return inferred_df
+
+
+def concat_derivate_series(
+    independent_full_df: pd.DataFrame,
+    derivate_trimmed_df: pd.DataFrame,
+    offsets_config: dict[str, Any],
+    force_trim: bool = False,
+) -> pd.DataFrame:
+
+    # useful when adding emergency fixed offsets
+    if force_trim:
+        independent_full_df: pd.DataFrame = process_raw_data(
+            trim(independent_full_df), **offsets_config
+        )
+
+    derivate_full_df: pd.DataFrame = process_raw_data(
+        derivate_trimmed_df, **offsets_config
+    )
+    full: pd.DataFrame = pd.concat(
+        [independent_full_df, derivate_full_df], axis=1
+    )
+    return full
+
+
+def collect_series(
+    config_dict: dict[str, Any], find: str = "series"
+) -> set[str]:
+    series: set[str] = set()
+    if find in config_dict:
+        config_series: dict[str, str] = config_dict[find]
+        series = series | set(config_series.keys())
+    for k, v in config_dict.items():
+        if k != find and isinstance(v, dict):
+            series = series | collect_series(v, find)
+    return series

tesorotools/main.py

@@ -0,0 +1,37 @@
+from pathlib import Path
+
+import docx
+import pandas as pd
+
+from tesorotools.artists.table import generate_tables_from_flash
+from tesorotools.render.content.table import render_table
+from tesorotools.utils.config import read_config
+from tesorotools.utils.globals import DEBUG, EXAMPLES
+
+if __name__ == "__main__":
+    # test tables here
+    table_config_file: Path = EXAMPLES / "tables.yaml"
+    offsets_config_file: Path = EXAMPLES / "offsets.yaml"
+
+    config_dicts = read_config(table_config_file)
+    offsets_config = read_config(offsets_config_file)
+
+    flash = pd.read_feather("derivates.feather")
+    generate_tables_from_flash(flash, config_dicts)
+
+    document = docx.Document("template.docx")
+    for table_path in (DEBUG / "table").iterdir():
+        if table_path.stem.endswith(("color", "shade")):
+            continue
+        table_dict = config_dicts[table_path.stem]
+        table: pd.DataFrame = pd.read_feather(table_path)
+        color: pd.DataFrame = pd.read_feather(
+            table_path.parent / f"{table_path.stem}_color.feather"
+        )
+        shade: pd.DataFrame = pd.read_feather(
+            table_path.parent / f"{table_path.stem}_shade.feather"
+        )
+
+        render_table(table, color, shade, document, **table_dict)
+        document.add_paragraph()
+    document.save("test.docx")