@@ -68,10 +68,10 @@ the `BigQuery quickstart guide
6868Data schema
6969-----------
7070
71- Linehaul writes an entry in a ``the-psf .pypi.file_downloads `` table for each
71+ Linehaul writes an entry in a ``bigquery-public-data .pypi.file_downloads `` table for each
7272download. The table contains information about what file was downloaded and how
7373it was downloaded. Some useful columns from the `table schema
74- <https://console.cloud.google.com/bigquery?pli=1&p=the-psf &d=pypi&t=file_downloads&page=table> `__
74+ <https://console.cloud.google.com/bigquery?pli=1&p=bigquery-public-data &d=pypi&t=file_downloads&page=table> `__
7575include:
7676
7777+------------------------+-----------------+-----------------------------+
@@ -108,7 +108,7 @@ The following query counts the total number of downloads for the project
108108
109109 #standardSQL
110110 SELECT COUNT(*) AS num_downloads
111- FROM `the-psf .pypi.file_downloads`
111+ FROM `bigquery-public-data .pypi.file_downloads`
112112 WHERE file.project = 'pytest'
113113 -- Only query the last 30 days of history
114114 AND DATE(timestamp)
@@ -118,7 +118,7 @@ The following query counts the total number of downloads for the project
118118+---------------+
119119| num_downloads |
120120+===============+
121- | 20531925 |
121+ | 26190085 |
122122+---------------+
123123
124124To only count downloads from pip, filter on the ``details.installer.name ``
@@ -128,7 +128,7 @@ column.
128128
129129 #standardSQL
130130 SELECT COUNT(*) AS num_downloads
131- FROM `the-psf .pypi.file_downloads`
131+ FROM `bigquery-public-data .pypi.file_downloads`
132132 WHERE file.project = 'pytest'
133133 AND details.installer.name = 'pip'
134134 -- Only query the last 30 days of history
@@ -139,7 +139,7 @@ column.
139139+---------------+
140140| num_downloads |
141141+===============+
142- | 19391645 |
142+ | 24334215 |
143143+---------------+
144144
145145Package downloads over time
@@ -154,7 +154,7 @@ filtering by this column reduces corresponding costs.
154154 SELECT
155155 COUNT(*) AS num_downloads,
156156 DATE_TRUNC(DATE(timestamp), MONTH) AS `month`
157- FROM `the-psf .pypi.file_downloads`
157+ FROM `bigquery-public-data .pypi.file_downloads`
158158 WHERE
159159 file.project = 'pytest'
160160 -- Only query the last 6 months of history
@@ -192,7 +192,7 @@ query processes over 500 GB of data.
192192 SELECT
193193 REGEXP_EXTRACT(details.python, r"[0-9]+\.[0-9]+") AS python_version,
194194 COUNT(*) AS num_downloads,
195- FROM `the-psf .pypi.file_downloads`
195+ FROM `bigquery-public-data .pypi.file_downloads`
196196 WHERE
197197 -- Only query the last 6 months of history
198198 DATE(timestamp)
@@ -204,17 +204,17 @@ query processes over 500 GB of data.
204204+--------+---------------+
205205| python | num_downloads |
206206+========+===============+
207- | 3.7 | 12990683561 |
207+ | 3.7 | 18051328726 |
208208+--------+---------------+
209- | 3.6 | 9035598511 |
209+ | 3.6 | 9635067203 |
210210+--------+---------------+
211- | 2.7 | 8467785320 |
211+ | 3.8 | 7781904681 |
212212+--------+---------------+
213- | 3.8 | 4581627740 |
213+ | 2.7 | 6381252241 |
214214+--------+---------------+
215- | 3.5 | 2412533601 |
215+ | null | 2026630299 |
216216+--------+---------------+
217- | null | 1641456718 |
217+ | 3.5 | 1894153540 |
218218+--------+---------------+
219219
220220Caveats
@@ -251,7 +251,7 @@ the official Python client library for BigQuery.
251251
252252 query_job = client.query("""
253253 SELECT COUNT(*) AS num_downloads
254- FROM `the-psf .pypi.file_downloads`
254+ FROM `bigquery-public-data .pypi.file_downloads`
255255 WHERE file.project = 'pytest'
256256 -- Only query the last 30 days of history
257257 AND DATE(timestamp)
@@ -274,7 +274,7 @@ Install `pypinfo`_ using pip.
274274
275275::
276276
277- pip install pypinfo
277+ python -m pip install pypinfo
278278
279279Usage:
280280
@@ -303,7 +303,7 @@ References
303303.. [# ] `PyPI Download Counts deprecation email <https://mail.python.org/pipermail/distutils-sig/2013-May/020855.html >`__
304304 .. [# ] `PyPI BigQuery dataset announcement email <https://mail.python.org/pipermail/distutils-sig/2016-May/028986.html >`__
305305
306- .. _public PyPI download statistics dataset : https://console.cloud.google.com/bigquery?p=the-psf &d=pypi&page=dataset
306+ .. _public PyPI download statistics dataset : https://console.cloud.google.com/bigquery?p=bigquery-public-data &d=pypi&page=dataset
307307.. _bandersnatch : /key_projects/#bandersnatch
308308.. _Google BigQuery : https://cloud.google.com/bigquery
309309.. _BigQuery web UI : https://console.cloud.google.com/bigquery
0 commit comments