from dagster_pandas import PandasColumn, create_dagster_pandas_dataframe_type
from pandas import DataFrame, read_csv
from dagster import OutputDefinition, pipeline, solid
from dagster.utils import script_relative_path
TripDataFrame = create_dagster_pandas_dataframe_type(
name="TripDataFrame",
columns=[
PandasColumn.integer_column("bike_id", min_value=0),
PandasColumn.categorical_column("color", categories={"red", "green", "blue"}),
PandasColumn.datetime_column(
"start_time", min_datetime=datetime(year=2020, month=2, day=10)
),
PandasColumn.datetime_column("end_time", min_datetime=datetime(year=2020, month=2, day=10)),
PandasColumn.string_column("station"),
PandasColumn.exists("amount_paid"),
PandasColumn.boolean_column("was_member"),
],
)
@solid(output_defs=[OutputDefinition(name="trip_dataframe", dagster_type=TripDataFrame)])
def load_trip_dataframe(_) -> DataFrame:
return read_csv(
script_relative_path("./ebike_trips.csv"),
parse_dates=["start_time", "end_time"],
date_parser=lambda x: datetime.strptime(x, "%Y-%m-%d %H:%M:%S.%f"),
)
from dagster import solid, SolidExecutionContext, Field, Array, String
from dagster_pandas import PandasColumn, create_dagster_pandas_dataframe_type
from pandas import DataFrame
from typing import Any, Optional, List, TYPE_CHECKING
from azmeta.access.resource_graph import query_dataframe
if TYPE_CHECKING:
ResourcesDataFrame = Any # DataFrame # Pandas has no type info yet.
else:
ResourcesDataFrame = create_dagster_pandas_dataframe_type(
name='ResourcesDataFrame',
columns=[
PandasColumn.string_column('resource_id'),
PandasColumn.string_column('subscription_id'),
],
)
@solid(
config_schema={
'subscriptions':
Field(Array(String),
description='The subscriptions to query in the Resource Graph.'),
'filters':
Field(String,
is_required=False,
description='Conditions for a KQL where operator.'),
'custom_projections':
Field(String,
is_required=False,
description='Assignments for a KQL project operator.'),
TripDataFrame = create_dagster_pandas_dataframe_type(
name='TripDataFrame',
columns=[
PandasColumn.integer_column('bike_id', min_value=0),
PandasColumn.categorical_column('color',
categories={'red', 'green', 'blue'}),
PandasColumn.datetime_column('start_time',
min_datetime=datetime(year=2020,
month=2,
day=10)),
PandasColumn.datetime_column('end_time',
min_datetime=datetime(year=2020,
month=2,
day=10)),
PandasColumn.string_column('station'),
PandasColumn.exists('amount_paid'),
PandasColumn.boolean_column('was_member'),
],
)
@solid(output_defs=[
OutputDefinition(name='trip_dataframe', dagster_type=TripDataFrame)
])
def load_trip_dataframe(_) -> DataFrame:
return read_csv(
script_relative_path('./ebike_trips.csv'),
parse_dates=['start_time', 'end_time'],
date_parser=lambda x: datetime.strptime(x, '%Y-%m-%d %H:%M:%S.%f'),
)
import functools
from azmeta.access.monitor_logs import (PerformanceCounterSpec,
query_dataframe_by_workspace_chunk,
build_perf_counter_percentile_query,
build_disk_percentile_query)
from azmeta.access.utils.chunking import build_grouped_chunk_list
from .resources import ResourcesDataFrame
from .specifications import AzureComputeSpecifications
if TYPE_CHECKING:
UtilizationDataFrame = Any # DataFrame # Pandas has no type info yet.
else:
UtilizationDataFrame = create_dagster_pandas_dataframe_type(
name='UtilizationDataFrame',
columns=[
PandasColumn.string_column('resource_id'),
PandasColumn.float_column('percentile_50th'),
PandasColumn.float_column('percentile_80th'),
PandasColumn.float_column('percentile_90th'),
PandasColumn.float_column('percentile_95th'),
PandasColumn.float_column('percentile_99th'),
PandasColumn.float_column('max'),
PandasColumn.integer_column('samples'),
],
)
@solid(required_resource_keys={'azure_monitor'})
def query_cpu_utilization(
context: SolidExecutionContext,
resources: ResourcesDataFrame) -> UtilizationDataFrame:
EventMetadataEntry.text(
max(dataframe["day"]),
"max_day",
"Maximum date of exchange rates",
),
EventMetadataEntry.text(
str(dataframe["day"].nunique()),
"num_unique_day",
"Total unique dates of exchange rates",
),
EventMetadataEntry.text(
str(dataframe["currency"].nunique()),
"num_unique_currency",
"Total unique currencies of exchange rates",
),
EventMetadataEntry.text(str(len(dataframe)), "n_rows",
"Number of rows seen in the dataframe"),
]
ExchangeRateDataFrame = create_dagster_pandas_dataframe_type(
name="ExchangeRateDataFrame",
columns=[
PandasColumn.string_column("id"),
PandasColumn.string_column("day"),
PandasColumn.string_column("currency"),
PandasColumn.numeric_column("rate"),
],
event_metadata_fn=compute_exchange_rate_dataframe_summary_statistics,
)