Skip to content

Commit

Permalink
[daggy-u] standardize indentation style across lessons
Browse files Browse the repository at this point in the history
  • Loading branch information
@cmpadden
cmpadden committed Feb 7, 2024
1 parent 0a93b7e commit 23e8203
Show file tree
Hide file tree
Showing 33 changed files with 460 additions and 460 deletions.
200 changes: 100 additions & 100 deletions ...-university/pages/dagster-essentials/extra-credit/asset-metadata-as-markdown.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -33,46 +33,46 @@ In Lesson 9, you created the `adhoc_request` asset. During materialization, the

@asset
def adhoc_request(config: AdhocRequestConfig, taxi_zones, taxi_trips, database: DuckDBResource):
"""
The response to an request made in the `requests` directory.
See `requests/README.md` for more information.
"""

# strip the file extension from the filename, and use it as the output filename
file_path = constants.REQUEST_DESTINATION_TEMPLATE_FILE_PATH.format(config.filename.split('.')[0])

# count the number of trips that picked up in a given borough, aggregated by time of day and hour of day
query = f"""
select
date_part('hour', pickup_datetime) as hour_of_day,
date_part('dayofweek', pickup_datetime) as day_of_week_num,
case date_part('dayofweek', pickup_datetime)
when 0 then 'Sunday'
when 1 then 'Monday'
when 2 then 'Tuesday'
when 3 then 'Wednesday'
when 4 then 'Thursday'
when 5 then 'Friday'
when 6 then 'Saturday'
end as day_of_week,
count(*) as num_trips
from trips
left join zones on trips.pickup_zone_id = zones.zone_id
where pickup_datetime >= '{config.start_date}'
and pickup_datetime < '{config.end_date}'
and pickup_zone_id in (
select zone_id
from zones
where borough = '{config.borough}'
)
group by 1, 2
order by 1, 2 asc
"""

with database.get_connection() as conn:
results = conn.execute(query).fetch_df()

fig = px.bar(
"""
The response to an request made in the `requests` directory.
See `requests/README.md` for more information.
"""

# strip the file extension from the filename, and use it as the output filename
file_path = constants.REQUEST_DESTINATION_TEMPLATE_FILE_PATH.format(config.filename.split('.')[0])

# count the number of trips that picked up in a given borough, aggregated by time of day and hour of day
query = f"""
select
date_part('hour', pickup_datetime) as hour_of_day,
date_part('dayofweek', pickup_datetime) as day_of_week_num,
case date_part('dayofweek', pickup_datetime)
when 0 then 'Sunday'
when 1 then 'Monday'
when 2 then 'Tuesday'
when 3 then 'Wednesday'
when 4 then 'Thursday'
when 5 then 'Friday'
when 6 then 'Saturday'
end as day_of_week,
count(*) as num_trips
from trips
left join zones on trips.pickup_zone_id = zones.zone_id
where pickup_datetime >= '{config.start_date}'
and pickup_datetime < '{config.end_date}'
and pickup_zone_id in (
select zone_id
from zones
where borough = '{config.borough}'
)
group by 1, 2
order by 1, 2 asc
"""

with database.get_connection() as conn:
results = conn.execute(query).fetch_df()

fig = px.bar(
results,
x="hour_of_day",
y="num_trips",
Expand All @@ -83,10 +83,10 @@ In Lesson 9, you created the `adhoc_request` asset. During materialization, the
"hour_of_day": "Hour of Day",
"day_of_week": "Day of Week",
"num_trips": "Number of Trips"
}
)
}
)

pio.write_image(fig, file_path)
pio.write_image(fig, file_path)
```

3. Add the `base64` and `MaterializeResult` imports to the top of the file:
Expand All @@ -100,7 +100,7 @@ In Lesson 9, you created the `adhoc_request` asset. During materialization, the

```python
with open(file_path, 'rb') as file:
image_data = file.read()
image_data = file.read()
```

5. Next, we’ll use base64 encoding to convert the chart to Markdown. After the `image_data` line, add the following code:
Expand Down Expand Up @@ -142,53 +142,53 @@ import base64
from . import constants

class AdhocRequestConfig(Config):
filename: str
borough: str
start_date: str
end_date: str
filename: str
borough: str
start_date: str
end_date: str

@asset
def adhoc_request(config: AdhocRequestConfig, taxi_zones, taxi_trips, database: DuckDBResource):
"""
The response to an request made in the `requests` directory.
See `requests/README.md` for more information.
"""

# strip the file extension from the filename, and use it as the output filename
file_path = constants.REQUEST_DESTINATION_TEMPLATE_FILE_PATH.format(config.filename.split('.')[0])

# count the number of trips that picked up in a given borough, aggregated by time of day and hour of day
query = f"""
select
date_part('hour', pickup_datetime) as hour_of_day,
date_part('dayofweek', pickup_datetime) as day_of_week_num,
case date_part('dayofweek', pickup_datetime)
when 0 then 'Sunday'
when 1 then 'Monday'
when 2 then 'Tuesday'
when 3 then 'Wednesday'
when 4 then 'Thursday'
when 5 then 'Friday'
when 6 then 'Saturday'
end as day_of_week,
count(*) as num_trips
from trips
left join zones on trips.pickup_zone_id = zones.zone_id
where pickup_datetime >= '{config.start_date}'
and pickup_datetime < '{config.end_date}'
and pickup_zone_id in (
select zone_id
from zones
where borough = '{config.borough}'
)
group by 1, 2
order by 1, 2 asc
"""

with database.get_connection() as conn:
results = conn.execute(query).fetch_df()

fig = px.bar(
"""
The response to an request made in the `requests` directory.
See `requests/README.md` for more information.
"""

# strip the file extension from the filename, and use it as the output filename
file_path = constants.REQUEST_DESTINATION_TEMPLATE_FILE_PATH.format(config.filename.split('.')[0])

# count the number of trips that picked up in a given borough, aggregated by time of day and hour of day
query = f"""
select
date_part('hour', pickup_datetime) as hour_of_day,
date_part('dayofweek', pickup_datetime) as day_of_week_num,
case date_part('dayofweek', pickup_datetime)
when 0 then 'Sunday'
when 1 then 'Monday'
when 2 then 'Tuesday'
when 3 then 'Wednesday'
when 4 then 'Thursday'
when 5 then 'Friday'
when 6 then 'Saturday'
end as day_of_week,
count(*) as num_trips
from trips
left join zones on trips.pickup_zone_id = zones.zone_id
where pickup_datetime >= '{config.start_date}'
and pickup_datetime < '{config.end_date}'
and pickup_zone_id in (
select zone_id
from zones
where borough = '{config.borough}'
)
group by 1, 2
order by 1, 2 asc
"""

with database.get_connection() as conn:
results = conn.execute(query).fetch_df()

fig = px.bar(
results,
x="hour_of_day",
y="num_trips",
Expand All @@ -199,22 +199,22 @@ def adhoc_request(config: AdhocRequestConfig, taxi_zones, taxi_trips, database:
"hour_of_day": "Hour of Day",
"day_of_week": "Day of Week",
"num_trips": "Number of Trips"
}
)
}
)

pio.write_image(fig, file_path)
pio.write_image(fig, file_path)

with open(file_path, 'rb') as file:
image_data = file.read()
with open(file_path, 'rb') as file:
image_data = file.read()

base64_data = base64.b64encode(image_data).decode('utf-8')
md_content = f"![Image](data:image/jpeg;base64,{base64_data})"
base64_data = base64.b64encode(image_data).decode('utf-8')
md_content = f"![Image](data:image/jpeg;base64,{base64_data})"

return MaterializeResult(
metadata={
"preview": MetadataValue.md(md_content)
}
)
return MaterializeResult(
metadata={
"preview": MetadataValue.md(md_content)
}
)
```

---
Expand Down
6 changes: 3 additions & 3 deletions ...ersity/pages/dagster-essentials/extra-credit/coding-practice-grouping-assets.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ For the assets in the `raw_files` and `ingested` groups, your assets should look

```python {% obfuscated="true" %}
@asset(
group_name="GROUP_NAME"
group_name="GROUP_NAME"
)
def name_of_asset():
```
Expand All @@ -36,8 +36,8 @@ For the `adhoc_request` asset, your code should look like this:

```python {% obfuscated="true" %}
request_assets = load_assets_from_modules(
modules=[requests],
group_name="requests",
modules=[requests],
group_name="requests",
)
```

Expand Down
32 changes: 16 additions & 16 deletions ...ges/dagster-essentials/extra-credit/coding-practice-metadata-taxi-zones-file.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,20 +22,20 @@ from dagster import MaterializeResult
group_name="raw_files",
)
def taxi_zones_file():
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
num_rows = MetadataValue.int(len(pd.read_csv(constants.TAXI_ZONES_FILE_PATH)))

return MaterializeResult(
metadata={
'Number of records': MetadataValue.int(num_rows)
}
)
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
num_rows = MetadataValue.int(len(pd.read_csv(constants.TAXI_ZONES_FILE_PATH)))

return MaterializeResult(
metadata={
'Number of records': MetadataValue.int(num_rows)
}
)
```
38 changes: 19 additions & 19 deletions ...pages/dagster-essentials/extra-credit/definition-metadata-asset-descriptions.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,15 @@ from dagster import asset

@asset
def taxi_zones_file():
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
```

---
Expand All @@ -47,18 +47,18 @@ For example:
from dagster import asset

@asset(
description="The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal."
description="The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal."
)
def taxi_zones_file():
"""
This will not show in the Dagster UI
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
"""
This will not show in the Dagster UI
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
```

---
Expand Down
24 changes: 12 additions & 12 deletions ...rsity/pages/dagster-essentials/extra-credit/definition-metadata-asset-groups.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -37,8 +37,8 @@ from dagster import load_assets_from_modules
from .assets import metrics

metric_assets = load_assets_from_modules(
modules=[metrics],
group_name="metrics",
modules=[metrics],
group_name="metrics",
)
```

Expand All @@ -54,18 +54,18 @@ You can also specify groups on individual assets by using the `group_name` param
from dagster import asset

@asset(
group_name="raw_files",
group_name="raw_files",
)
def taxi_zones_file():
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
"""
The raw CSV file for the taxi zones dataset. Sourced from the NYC Open Data portal.
"""
raw_taxi_zones = requests.get(
"https://data.cityofnewyork.us/api/views/755u-8jsi/rows.csv?accessType=DOWNLOAD"
)

with open(constants.TAXI_ZONES_FILE_PATH, "wb") as output_file:
output_file.write(raw_taxi_zones.content)
```

In this example, the `taxi_zones_file` asset is grouped into the `raw_files` asset group.
Expand Down
Loading

0 comments on commit 23e8203

Please sign in to comment.