Diff Path

View or edit on GitHub

This page is synchronized from trase/models/Diff - Path.ipynb. Last modified on 2025-12-10 18:30 CET by Trase Admin. Please view or edit the original file there; changes should be reflected here after a midnight build (CET time), or manually triggering it with a GitHub action (link).

import sys
from io import BytesIO
from pathlib import PurePosixPath

import pandas as pd
from boto3 import client
from trase.tools.aws import get_pandas_df
from trase.tools.jupyter.diff import print_difference, read_csv

df_b = read_csv("Ecuador/Shrimp/2019/POST/results.csv")
df_a = get_pandas_df("ecuador/shrimp/sei_pcs/v1.0.0/SEIPCS_ECUADOR_SHRIMP_2019.csv")
# df_b = get_pandas_df("ecuador/shrimp/sei_pcs/SEIPCS_ECUADOR_SHRIMP_2019.csv")

# assert 30616 not in list(df_b.HS6.unique())
print((32000 / df_b.VOLUME_RAW.sum()) * 100)

print_difference(
    df_a,
    df_b,
)

from trase.tools.aws import get_pandas_df
from trase.diff import print_difference, read_csv

df_a = get_pandas_df("brazil/coffee/sei_pcs/qa_ed/SEIPCS_BRAZIL_COFFEE_2015.csv")
df_b = get_pandas_df(
    "brazil/coffee/sei_pcs/qa_ed/post-processed/SEIPCS_BRAZIL_COFFEE_2015.csv"
)


print_difference(
    df_a,
    df_b[
        [
            "COUNTRY_OF_ORIGIN",
            "COMODITY",
            "YEAR",
            "EXPORTER",
            "EXPORTER_TAX_ID",
            "LVL3_NAME_PROD",
            "PORT_OF_EXPORT",
            "COUNTRY_OF_DESTINATION",
            "IMPORTER",
            "VOLUME_RAW",
            "VOLUME_NORM",
            "FOB",
            "BRANCH",
            "PRODUCT",
            "STATUS",
            "LVL6_GEOCODE_PROD",
            "LVL6_NAME_PROD",
            "LVL6_GEOCODE_LH",
            "LVL6_NAME_LH",
            "QA_EXPORT_MUN",
        ]
    ],
)

import pandas as pd

df = pd.read_csv("Ecuador/Shrimp/2019/POST/results.csv", sep=";")
print(df.columns)
df[df.EXPORTER.str.startswith("LABORATORIO BAMAR")].BRANCH.unique()
# SODERAL SOCIEDAD DE DESTILACION DE ALCOHOLES S.A.
# SODERAL SOCIEDAD DE DESTILACION DE ALCOHOLES S.A.

from trase.tools.ingest.metadata import (
    get_dataset_file_id_list,
    get_dataset_file_metadata,
)

file_ids = get_dataset_file_id_list(7)
metadata = get_dataset_file_metadata(7, file_ids[0])
node_list = metadata["nodes"]
# print(sorted(node_list, key=lambda i: i['node_position']))
for node_data in node_list:
    print(node_data)

df_b.columns