querysource 4.4.0__tar.gz → 4.4.2__tar.gz

querysource-4.4.2/.pre-commit-config.yaml

@@ -0,0 +1,21 @@
+# Pre-commit hooks for QuerySource.
+#
+# Install once per clone (inside the activated venv):
+#     uv pip install pre-commit
+#     pre-commit install
+#
+# The generate-multiquery-docs hook regenerates the per-component JSON under
+# generated/ from the component classes + their <module>.catalog.yaml companion
+# files. If anything changed, pre-commit re-stages the files and fails the
+# commit so the refreshed docs are included — this is the freshness guard that
+# stops generated/ from drifting out of sync with the source of truth.
+repos:
+  - repo: local
+    hooks:
+      - id: generate-multiquery-docs
+        name: Regenerate MultiQuery component docs (generated/)
+        entry: bash -c 'generate-multiquery-docs -o generated >/dev/null && git add generated'
+        language: system
+        pass_filenames: false
+        always_run: true
+        stages: [pre-commit]

{querysource-4.4.0 → querysource-4.4.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: querysource
-Version: 4.4.0
+Version: 4.4.2
 Summary: Aiohttp web service for querying several databases easily
 Author-email: Jesus Lara <jesuslarag@gmail.com>
 License: BSD-3-Clause

querysource-4.4.2/generated/DropCols.json

@@ -0,0 +1,109 @@
+{
+  "name": "DropCols",
+  "category": "Transformations",
+  "description": "Drop the columns matching any of the provided selectors (blacklist by column name).",
+  "usage": "Provide at least one of ``columns`` (exact names), ``pattern`` (glob), ``regex``, ``startswith`` or ``endswith``. Matches from every selector are unioned and removed. Exact names in ``columns`` that are not present are silently ignored.",
+  "attributes": [
+    {
+      "name": "columns",
+      "type": "list",
+      "default": null,
+      "required": false,
+      "description": "Exact column names to drop. Missing columns are silently ignored."
+    },
+    {
+      "name": "pattern",
+      "type": "str",
+      "default": null,
+      "required": false,
+      "description": "Glob/fnmatch pattern to match column names (e.g. \"debug_*\")."
+    },
+    {
+      "name": "regex",
+      "type": "str",
+      "default": null,
+      "required": false,
+      "description": "Regular expression to match column names (e.g. \"^tmp_.*$\")."
+    },
+    {
+      "name": "startswith",
+      "type": "list",
+      "default": null,
+      "required": false,
+      "description": "Drop columns whose name starts with any of these prefixes."
+    },
+    {
+      "name": "endswith",
+      "type": "list",
+      "default": null,
+      "required": false,
+      "description": "Drop columns whose name ends with any of these suffixes."
+    }
+  ],
+  "json_schema": {
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "DropCols",
+    "type": "object",
+    "properties": {
+      "columns": {
+        "$ref": "#/$defs/stringList",
+        "description": "Exact column names to drop."
+      },
+      "pattern": {
+        "type": "string",
+        "description": "Glob/fnmatch pattern to match column names (e.g. \"debug_*\")."
+      },
+      "regex": {
+        "type": "string",
+        "description": "Regular expression to match column names (e.g. \"^tmp_.*$\")."
+      },
+      "startswith": {
+        "$ref": "#/$defs/stringList",
+        "description": "Prefixes; columns starting with any are dropped."
+      },
+      "endswith": {
+        "$ref": "#/$defs/stringList",
+        "description": "Suffixes; columns ending with any are dropped."
+      }
+    },
+    "anyOf": [
+      {
+        "required": [
+          "columns"
+        ]
+      },
+      {
+        "required": [
+          "pattern"
+        ]
+      },
+      {
+        "required": [
+          "regex"
+        ]
+      },
+      {
+        "required": [
+          "startswith"
+        ]
+      },
+      {
+        "required": [
+          "endswith"
+        ]
+      }
+    ],
+    "additionalProperties": true,
+    "description": "Drop columns matching any selector. At least one selector is required.",
+    "$defs": {
+      "stringList": {
+        "type": "array",
+        "items": {
+          "type": "string"
+        }
+      }
+    }
+  },
+  "example": "{\"Transform\": [{\"DropCols\": {\"columns\": [\"internal_id\", \"debug_flag\"]}}]}",
+  "icon": "shuffle"
+}

querysource-4.4.2/generated/Filter.json

@@ -0,0 +1,174 @@
+{
+  "name": "Filter",
+  "category": "Operators",
+  "description": "Filter the rows of a DataFrame using declarative conditions, named filter functions, and/or column equality selection, combined with a logical AND/OR.",
+  "usage": "Provide any combination of: ``conditions``/``filter`` (a list of ``{column, expression, value}`` specs built by create_filter), ``fields`` (a column-to-value equality selection), and ``filter_conditions`` (a mapping of named filter function to its keyword arguments). ``operator`` chooses how the ``filter`` conditions are combined \u2014 ``&`` (AND, default) or ``|`` (OR). All inputs are optional and may be used together.",
+  "attributes": [
+    {
+      "name": "fields",
+      "type": "dict",
+      "default": {},
+      "required": false,
+      "description": "Column-to-value equality selection: keep only rows where each column equals the given value (a list value matches any of its entries)."
+    },
+    {
+      "name": "operator",
+      "type": "str",
+      "default": "&",
+      "required": false,
+      "description": "Logical operator joining the ``filter`` conditions \u2014 ``&`` (AND, default) or ``|`` (OR)."
+    },
+    {
+      "name": "conditions",
+      "type": "list",
+      "default": null,
+      "required": false,
+      "description": "List of filter conditions in create_filter format (``{column, expression, value}``). Optional; combinable with ``filter`` and ``filter_conditions``."
+    },
+    {
+      "name": "filter",
+      "type": "list",
+      "default": [],
+      "required": false,
+      "description": "List of filter specs (same ``{column, expression, value}`` format as ``conditions``) passed to create_filter; the resulting masks are joined with ``operator``."
+    },
+    {
+      "name": "filter_conditions",
+      "type": "dict",
+      "default": {},
+      "required": false,
+      "description": "Mapping of named filter function (from querysource.types.dt.filters) to its keyword arguments, applied in order before the other filters."
+    }
+  ],
+  "json_schema": {
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "Filter",
+    "type": "object",
+    "properties": {
+      "fields": {
+        "type": "object",
+        "description": "Column equality filter \u2014 {column: value | [values]}.",
+        "additionalProperties": {
+          "description": "Value (or list of values, OR-combined) the column must equal."
+        },
+        "default": {}
+      },
+      "operator": {
+        "type": "string",
+        "enum": [
+          "&",
+          "|"
+        ],
+        "description": "Logical operator joining the ``filter`` conditions \u2014 ``&`` (AND, default) or ``|`` (OR).",
+        "default": "&"
+      },
+      "conditions": {
+        "type": "array",
+        "description": "Filter conditions (create_filter format).",
+        "items": {
+          "$ref": "#/$defs/filterCondition"
+        }
+      },
+      "filter": {
+        "type": "array",
+        "description": "Filter specs (create_filter format).",
+        "items": {
+          "$ref": "#/$defs/filterCondition"
+        },
+        "default": []
+      },
+      "filter_conditions": {
+        "type": "object",
+        "description": "Named filter functions and their keyword arguments.",
+        "propertyNames": {
+          "$ref": "#/$defs/filterFunc"
+        },
+        "additionalProperties": {
+          "type": "object",
+          "description": "Keyword arguments forwarded to the filter function."
+        },
+        "default": {}
+      }
+    },
+    "additionalProperties": true,
+    "description": "Reduce a DataFrame to the rows satisfying the given conditions / functions / field selections (SQL WHERE-like).",
+    "$defs": {
+      "filterExpression": {
+        "type": "string",
+        "description": "Comparison or text/null operator applied to a column. ``expression`` may also be a list to chain operators (create_filter_chain).",
+        "enum": [
+          "==",
+          "!=",
+          ">",
+          "<",
+          ">=",
+          "<=",
+          "gt",
+          "lt",
+          "contains",
+          "not_contains",
+          "startswith",
+          "not_startswith",
+          "endswith",
+          "not_endswith",
+          "regex",
+          "not_regex",
+          "fullmatch",
+          "is_null",
+          "not_null",
+          "is_empty",
+          "func",
+          "function"
+        ]
+      },
+      "filterCondition": {
+        "type": "object",
+        "description": "A single create_filter condition.",
+        "properties": {
+          "column": {
+            "type": "string",
+            "description": "Column to test (must exist in the DataFrame)."
+          },
+          "expression": {
+            "default": "==",
+            "description": "Comparison operator, or a list of operators to chain. Defaults to ``==``.",
+            "oneOf": [
+              {
+                "$ref": "#/$defs/filterExpression"
+              },
+              {
+                "type": "array",
+                "items": {
+                  "$ref": "#/$defs/filterExpression"
+                }
+              }
+            ]
+          },
+          "value": {
+            "description": "Value to compare against \u2014 a scalar, ``{\"$column\": \"other_col\"}`` for column-to-column comparison, or a function name when ``expression`` is ``func``/``function``. Omitted for ``is_null``/``not_null``/``is_empty``."
+          }
+        },
+        "required": [
+          "column"
+        ],
+        "additionalProperties": true
+      },
+      "filterFunc": {
+        "type": "string",
+        "description": "Named filter function from querysource.types.dt.filters.",
+        "enum": [
+          "drop_columns",
+          "drop_rows",
+          "drop_duplicates",
+          "clean_empty",
+          "suppress",
+          "fill_na",
+          "fill_nulls",
+          "drop_na"
+        ]
+      }
+    }
+  },
+  "example": "{\n  \"Filter\": {\n    \"conditions\": [\n      {\"column\": \"status\", \"expression\": \"==\", \"value\": \"active\"},\n      {\"column\": \"revenue\", \"expression\": \">\", \"value\": 1000}\n    ],\n    \"operator\": \"&\"\n  }\n}",
+  "icon": "filter"
+}

querysource-4.4.2/generated/FilterCols.json

@@ -0,0 +1,38 @@
+{
+  "name": "FilterCols",
+  "category": "Transformations",
+  "description": "Drop columns matching a predefined data-quality predicate (filters by content, not by column name).",
+  "usage": "Set ``expression`` to one predefined predicate: ``all_null`` (drop columns entirely NaN/None), ``all_empty`` (entirely NaN/None/empty-string), or ``constant`` (all non-null values identical; all-null columns are left to ``all_null``).",
+  "attributes": [
+    {
+      "name": "expression",
+      "type": "str",
+      "default": null,
+      "required": true,
+      "description": "Predefined data-quality predicate selecting which columns to drop."
+    }
+  ],
+  "json_schema": {
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "FilterCols",
+    "type": "object",
+    "properties": {
+      "expression": {
+        "type": "string",
+        "description": "Data-quality predicate.",
+        "enum": [
+          "all_empty",
+          "all_null",
+          "constant"
+        ]
+      }
+    },
+    "required": [
+      "expression"
+    ],
+    "additionalProperties": true,
+    "description": "Drop columns by data content. ``expression`` is required."
+  },
+  "example": "{\"Transform\": [{\"FilterCols\": {\"expression\": \"all_null\"}}]}",
+  "icon": "shuffle"
+}

querysource-4.4.2/generated/Forecast.json

@@ -0,0 +1,184 @@
+{
+  "name": "Forecast",
+  "category": "Transformations",
+  "description": "Generate time-series forecasts (ARIMA, SARIMA, or Exponential Smoothing), fitting a model to the values in the target column(s) and appending ``steps`` future predictions to the result.",
+  "usage": "Set ``index_column`` (the datetime index), the target series via ``columns`` (list) or ``value_column`` (single column), and ``model``. ``steps`` controls how many future periods to predict and ``frequency`` their spacing. ARIMA/SARIMA use the ``order`` (p,d,q); SARIMA and Exponential require ``by_group`` to forecast each group separately.",
+  "attributes": [
+    {
+      "name": "steps",
+      "type": "int",
+      "default": 6,
+      "required": false,
+      "description": "Number of future periods to forecast. Default ``6``."
+    },
+    {
+      "name": "frequency",
+      "type": "str",
+      "default": "ME",
+      "required": false,
+      "description": "Pandas offset alias for the spacing of forecasted periods \u2014 e.g. ``D`` (daily), ``W`` (weekly), ``MS`` (month-start), ``ME`` (month-end, default), ``QE`` (quarter-end), ``YE`` (year-end), ``h`` (hourly). Drives the ARIMA forecast date range; Exponential always resamples monthly (``MS``) and SARIMA works in monthly periods."
+    },
+    {
+      "name": "model_args",
+      "type": "dict",
+      "default": {},
+      "required": false,
+      "description": "Extra keyword arguments forwarded to the model (currently used by ``Exponential``, e.g. ``alpha``)."
+    },
+    {
+      "name": "reset_index",
+      "type": "bool",
+      "default": true,
+      "required": false,
+      "description": "If ``True`` (default), reset the result index after forecasting."
+    },
+    {
+      "name": "order",
+      "type": "list",
+      "default": [
+        1,
+        1,
+        1
+      ],
+      "required": false,
+      "description": "ARIMA/SARIMA ``(p, d, q)`` order \u2014 autoregressive, differencing, and moving-average terms. Default ``[1, 1, 1]``."
+    },
+    {
+      "name": "index_column",
+      "type": "str",
+      "default": null,
+      "required": true,
+      "description": "Name of the datetime column used as the time-series index."
+    },
+    {
+      "name": "columns",
+      "type": "list",
+      "default": null,
+      "required": false,
+      "description": "Column(s) to forecast. Each produces its own predictions. Either this or ``value_column`` is required."
+    },
+    {
+      "name": "value_column",
+      "type": "str",
+      "default": null,
+      "required": false,
+      "description": "Single-column alias for ``columns`` (promoted to a one-element list when ``columns`` is not provided)."
+    },
+    {
+      "name": "model",
+      "type": "str",
+      "default": null,
+      "required": true,
+      "description": "Forecast model. ARIMA = non-seasonal AutoRegressive Integrated Moving Average (per-column, no grouping). SARIMA = Seasonal ARIMA (SARIMAX with a monthly seasonal order (1,1,1,12)); requires ``by_group``. Exponential = Holt-Winters Exponential Smoothing (additive trend + additive seasonal, damped; resamples monthly, needs >= 2x ``steps`` points per series); requires ``by_group``."
+    },
+    {
+      "name": "by_group",
+      "type": "str",
+      "default": null,
+      "required": false,
+      "description": "Column to group rows by, forecasting each group independently. Required for ``SARIMA`` and ``Exponential``; ignored by ``ARIMA``."
+    }
+  ],
+  "json_schema": {
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "Forecast",
+    "type": "object",
+    "properties": {
+      "steps": {
+        "type": "integer",
+        "description": "Number of future periods to forecast. Default ``6``.",
+        "default": 6
+      },
+      "frequency": {
+        "type": "string",
+        "description": "Pandas offset alias for the spacing of forecasted periods \u2014 e.g. ``D`` (daily), ``W`` (weekly), ``MS`` (month-start), ``ME`` (month-end, default), ``QE`` (quarter-end), ``YE`` (year-end), ``h`` (hourly). Drives the ARIMA forecast date range; Exponential always resamples monthly (``MS``) and SARIMA works in monthly periods.",
+        "default": "ME"
+      },
+      "model_args": {
+        "type": "object",
+        "description": "Extra keyword arguments forwarded to the model (currently used by ``Exponential``, e.g. ``alpha``).",
+        "default": {}
+      },
+      "reset_index": {
+        "type": "boolean",
+        "description": "If ``True`` (default), reset the result index after forecasting.",
+        "default": true
+      },
+      "order": {
+        "type": "array",
+        "items": {
+          "type": "integer"
+        },
+        "minItems": 3,
+        "maxItems": 3,
+        "description": "ARIMA (p, d, q) order.",
+        "default": [
+          1,
+          1,
+          1
+        ]
+      },
+      "index_column": {
+        "type": "string",
+        "description": "Name of the datetime column used as the time-series index."
+      },
+      "columns": {
+        "$ref": "#/$defs/columnRef",
+        "description": "Numeric column(s) to forecast."
+      },
+      "value_column": {
+        "type": "string",
+        "description": "Single-column alias for ``columns`` (promoted to a one-element list when ``columns`` is not provided)."
+      },
+      "model": {
+        "type": "string",
+        "description": "Forecast model name.",
+        "enum": [
+          "ARIMA",
+          "SARIMA",
+          "Exponential"
+        ]
+      },
+      "by_group": {
+        "type": "string",
+        "description": "Column to group rows by, forecasting each group independently. Required for ``SARIMA`` and ``Exponential``; ignored by ``ARIMA``."
+      }
+    },
+    "required": [
+      "index_column",
+      "model"
+    ],
+    "anyOf": [
+      {
+        "required": [
+          "columns"
+        ]
+      },
+      {
+        "required": [
+          "value_column"
+        ]
+      }
+    ],
+    "additionalProperties": true,
+    "description": "Append time-series forecasts to a DataFrame. ``index_column`` and ``model`` are required, plus one of ``columns`` / ``value_column``.",
+    "$defs": {
+      "columnRef": {
+        "description": "A single column name or a list of column names.",
+        "oneOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "array",
+            "items": {
+              "type": "string"
+            }
+          }
+        ]
+      }
+    }
+  },
+  "example": "{\n  \"Transform\": [\n    {\n      \"Forecast\": {\n        \"index_column\": \"date\",\n        \"value_column\": \"revenue\",\n        \"model\": \"ARIMA\",\n        \"steps\": 12,\n        \"frequency\": \"ME\"\n      }\n    }\n  ]\n}",
+  "icon": "shuffle"
+}

querysource-4.4.2/generated/GoogleMaps.json

@@ -0,0 +1,82 @@
+{
+  "name": "GoogleMaps",
+  "category": "Transformations",
+  "description": "Enrich a DataFrame with Google Maps route geometry, distance, and travel-time data (calls the navigator Google Maps Route API per row).",
+  "usage": "Operates on rows that contain an ``origin`` and a ``locations`` list (each location with latitude/longitude/location_name/store_id). Locations are sorted by ``timestamp_key`` and a waypoint route (plus an optimal route) is computed, adding route/distance/duration columns (and ``opt_*`` variants).",
+  "attributes": [
+    {
+      "name": "zoom",
+      "type": "int",
+      "default": 10,
+      "required": false,
+      "description": "Map zoom level for any embedded map output. Default ``10``."
+    },
+    {
+      "name": "map_scale",
+      "type": "int",
+      "default": 2,
+      "required": false,
+      "description": "Scale factor for map output (1 or 2). Default ``2``."
+    },
+    {
+      "name": "timestamp_key",
+      "type": "str",
+      "default": "timestamp",
+      "required": false,
+      "description": "Column inside each ``locations`` entry used to sort stops by departure time. Default ``timestamp``."
+    },
+    {
+      "name": "departure_time",
+      "type": "str",
+      "default": null,
+      "required": false,
+      "description": "Fixed departure time (ISO string) used when a row has no per-row ``departure_time``. Default ``None``."
+    },
+    {
+      "name": "type",
+      "type": "str",
+      "default": "get_route",
+      "required": false,
+      "description": "Route method (navigator ``Route``) to dispatch: ``get_route`` (origin\u2192destination route) or ``waypoint_route`` (multi-stop route). An optimal-route pass is also computed and added as ``opt_*`` columns."
+    }
+  ],
+  "json_schema": {
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "title": "GoogleMaps",
+    "type": "object",
+    "properties": {
+      "zoom": {
+        "type": "integer",
+        "description": "Map zoom level for any embedded map output. Default ``10``.",
+        "default": 10
+      },
+      "map_scale": {
+        "type": "integer",
+        "description": "Scale factor for map output (1 or 2). Default ``2``.",
+        "default": 2
+      },
+      "timestamp_key": {
+        "type": "string",
+        "description": "Column inside each ``locations`` entry used to sort stops by departure time. Default ``timestamp``.",
+        "default": "timestamp"
+      },
+      "departure_time": {
+        "type": "string",
+        "description": "Fixed departure time (ISO string) used when a row has no per-row ``departure_time``. Default ``None``."
+      },
+      "type": {
+        "type": "string",
+        "description": "Route method to dispatch.",
+        "default": "get_route",
+        "enum": [
+          "get_route",
+          "waypoint_route"
+        ]
+      }
+    },
+    "additionalProperties": true,
+    "description": "Add Google Maps route/travel-time columns to a DataFrame."
+  },
+  "example": "{\n  \"Transform\": [\n    {\n      \"GoogleMaps\": {\n        \"zoom\": 12,\n        \"timestamp_key\": \"departure_time\",\n        \"type\": \"get_route\"\n      }\n    }\n  ]\n}",
+  "icon": "shuffle"
+}