Merge final release (#1)

* adding initial skeleton * updating .gitignore * updating dev dependencies * adding report.py * updating notes * adding prospector.yaml * updating beam to install gcp extras * adding documentation * adding data exploration report + code * adding latest beam pipeline code * adding latest beam pipeline code * adding debug.py * adding latesty beam pipeline code * adding latest beam pipeline code * adding latest beam pipeline code * updating .gitignore * updating folder structure for data input/output * updating prospector.yaml * adding latest beam pipeline code * updating prospector.yaml * migrate beam pipeline to main.py * updating .gitignore * updating .gitignore * adding download script for data set * adding initial docs * moving inputs/outputs to use pathlib * removing shard_name_template from output file * adding pyenv 3.7.9 * removing requirements.txt for documentation * updating README.md * updating download data script for new location in GCS * adding latest beam pipeline code for dataflow * adding latest beam pipeline code for dataflow * adding latest beam pipeline code for dataflow * moving dataflow notes * updating prospector.yaml * adding latest beam pipeline code for dataflow * updating beam pipeline to use GroupByKey * updating download_data script with new bucket * update prospector.yaml * update dataflow documentation with new commands for vpc * adding latest beam pipeline code for dataflow with group optimisation * updating dataflow documentation * adding latest beam pipeline code for dataflow with group optimisation * updating download_data script with pp-2020 dataset * adding temporary notes * updating dataflow notes * adding latest beam pipeline code * updating dataflow notes * adding latest beam pipeline code for dataflow * adding debug print * moving panda-profiling report into docs * updating report.py * adding entrypoint command * adding initial docs * adding commands.md to notes * commenting out debug imports * updating documentation * updating latest beam pipeline with default inputs * updating poetry * adding requirements.txt * updating documentation
2025-12-22 03:55:43 +00:00 · 2021-09-28 00:31:09 +01:00
parent 8a22bfebe1
commit 80376a662e
34 changed files with 5667 additions and 1 deletions
--- a/exploration/report.py
+++ b/exploration/report.py
@@ -0,0 +1,38 @@
+import pathlib
+
+import pandas as pd
+from pandas_profiling import ProfileReport
+
+
+def main():
+    input_file = (
+        pathlib.Path(__file__).parents[1] / "data" / "input" / "pp-complete.csv"
+    )
+    with input_file.open() as csv:
+        df_report = pd.read_csv(
+            csv,
+            names=[
+                "transaction_id",
+                "price",
+                "date_of_transfer",
+                "postcode",
+                "property_type",
+                "old_new",
+                "duration",
+                "paon",
+                "saon",
+                "street",
+                "locality",
+                "town_city",
+                "district",
+                "county",
+                "ppd_category",
+                "record_status",
+            ],
+        )
+    profile = ProfileReport(df_report, title="Price Paid Data", minimal=True)
+    profile.to_file("price_paid_data_report.html")
+
+
+if __name__ == "__main__":
+    main()