Main

View or edit on GitHub

This page is synchronized from trase/models/argentina/soy/main.ipynb. Last modified on 2026-08-05 15:56 CEST by Harry Biddle. 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).

%configure_logging

from trase.tools.sps import SupplyChain

for year in [2015, 2016, 2017, 2018, 2019]:
    supplychain = SupplyChain("argentina/soy", year)
    supplychain.preparation()
    supplychain.load()
    supplychain.run()
    supplychain.flow_report_by_attribute(
        "vol_bean", ["status", "branch"], significant_digits=10
    )
    supplychain.export_results()
    supplychain.upload_results()

from trase.tools.sps import SupplyChain

supplychain = SupplyChain("argentina/soy", year=2019)
supplychain.preparation()

Extracting data from source ...[0mDownloading s3://trase-storage/argentina/national/sei_pcs/v0.2.2/CD_ARGENTINA_2019_SOY.csv[0m
    [97m took 0.1 seconds[0m
[1mRunning pre-processing for Flows[0m
Report: Before processing[0m
        | Row Count: 936[0m
        | Sum of vol_bean: 53,580,604[0m
        | Sum of fob: 18,572,442,802[0m
Report: Drop vol_bean=0[0m
        | Row Count: 936[0m
        | Sum of vol_bean: 53,580,604[0m
        | Sum of fob: 18,572,442,802[0m


/home/sagemaker-user/.admin/repos/TRASE/trase/tools/etl/pandas_wrapper.py:397: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[column_name] = _cast_series_to_type(df[column_name], python_type)
/home/sagemaker-user/.admin/repos/TRASE/trase/tools/etl/pandas_wrapper.py:397: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[column_name] = _cast_series_to_type(df[column_name], python_type)
/home/sagemaker-user/.admin/repos/TRASE/trase/tools/etl/pandas_wrapper.py:397: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[column_name] = _cast_series_to_type(df[column_name], python_type)


Report: After processing[0m
        | Row Count: 936[0m
        | Sum of vol_bean: 53,580,604[0m
        | Sum of fob: 18,572,442,802[0m
[32mWritten /home/sagemaker-user/.admin/repos/TRASE/trase/models/argentina/soy/2019/prepared/flows.csv[0m
Extracting data from source ...[0mDownloading s3://trase-storage/argentina/spatial/BOUNDARIES/provinces/out/AR_PROVINCES.csv[0m


    [97m took 0.1 seconds[0m
[1mRunning pre-processing for Provinces[0m
Report: Before processing[0m
        | Row Count: 24[0m


/home/sagemaker-user/.admin/repos/TRASE/trase/tools/etl/pandas_wrapper.py:397: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df[column_name] = _cast_series_to_type(df[column_name], python_type)



---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

Cell In[2], line 3
      1 from trase.tools.sps import SupplyChain
      2 supplychain = SupplyChain("argentina/soy", year=2019)
----> 3 supplychain.preparation()


File ~/.admin/repos/TRASE/trase/tools/sei_pcs/utilities.py:104, in trace_memory_allocation.<locals>.wrapper(*args, **kwargs)
    102     return return_value
    103 else:
--> 104     return func(*args, **kwargs)


File ~/.admin/repos/TRASE/trase/tools/sei_pcs/supply_chain.py:199, in SupplyChain.preparation(self)
    197     OUTPUT_FILE_OVERWRITE_TRACKER.enable()
    198     with warnings_if_pd_merge_called_without_validate():
--> 199         self._call_scripts_with_function(
    200             self.preparation_scripts, "preparation", self.context
    201         )
    202 finally:
    203     OUTPUT_FILE_OVERWRITE_TRACKER.disable()


File ~/.admin/repos/TRASE/trase/tools/sei_pcs/supply_chain.py:266, in SupplyChain._call_scripts_with_function(self, scripts, function_name, *function_arguments)
    262         continue
    264     LOGGER.info(f"Running {function_name} from {script_file}")
--> 266     return_value = function(*function_arguments)
    267     results.append(return_value)
    269 return results


File ~/.admin/repos/TRASE/trase/models/argentina/soy/preparation.py:39, in preparation(context)
     36 Flows(context).run()
     38 # Boundaries
---> 39 Provinces(context).run()
     40 df_departments = Departments(context).run()
     41 Zone(context).run(df_departments)


File ~/.admin/repos/TRASE/trase/tools/etl_internal/processors.py:109, in Preprocessor.run(self, returns, *args)
    106         self._extract_from_source()
    108 if self.should_rerun(args):
--> 109     return super(DataframePreprocessor, self).run(
    110         *args, returns=returns, force=True
    111     )
    112 else:
    113     return super(DataframePreprocessor, self).run(
    114         *args, returns=returns, prevent=True
    115     )


File ~/.admin/repos/TRASE/trase/tools/etl/processors.py:177, in PreprocessorBase.run(self, returns, force, prevent, *args)
    174     data = self.preprocess(data)
    176 with timing("Processing data", indent=1):
--> 177     data = self.process(data, *args)
    178     assert data is not None, "process() must return a value"
    180 with timing("Post-processing data", indent=1):


File ~/.admin/repos/TRASE/trase/models/argentina/soy/preparation.py:139, in Provinces.process(self, df)
    138 def process(self, df):
--> 139     return append(
    140         df,
    141         [
    142             {"geocode": "XX", "trase_id": "AR-XX", "name": "UNKNOWN"},
    143             {"geocode": "XX-STOCK", "trase_id": "AR-XX-STOCK", "name": "STOCK"},
    144         ],
    145     )


File ~/.admin/repos/TRASE/trase/tools/sei_pcs/pandas_utilities.py:705, in append(df, items)
    704 def append(df: pd.DataFrame, items) -> pd.DataFrame:
--> 705     return pd.concat([df, items], ignore_index=True, verify_integrity=True)


File ~/.conda/envs/trase-env/lib/python3.10/site-packages/pandas/core/reshape/concat.py:382, in concat(objs, axis, join, ignore_index, keys, levels, names, verify_integrity, sort, copy)
    379 elif copy and using_copy_on_write():
    380     copy = False
--> 382 op = _Concatenator(
    383     objs,
    384     axis=axis,
    385     ignore_index=ignore_index,
    386     join=join,
    387     keys=keys,
    388     levels=levels,
    389     names=names,
    390     verify_integrity=verify_integrity,
    391     copy=copy,
    392     sort=sort,
    393 )
    395 return op.get_result()


File ~/.conda/envs/trase-env/lib/python3.10/site-packages/pandas/core/reshape/concat.py:448, in _Concatenator.__init__(self, objs, axis, join, keys, levels, names, ignore_index, verify_integrity, copy, sort)
    445 objs, keys = self._clean_keys_and_objs(objs, keys)
    447 # figure out what our result ndim is going to be
--> 448 ndims = self._get_ndims(objs)
    449 sample, objs = self._get_sample_object(objs, ndims, keys, names, levels)
    451 # Standardize axis parameter to int


File ~/.conda/envs/trase-env/lib/python3.10/site-packages/pandas/core/reshape/concat.py:489, in _Concatenator._get_ndims(self, objs)
    484     if not isinstance(obj, (ABCSeries, ABCDataFrame)):
    485         msg = (
    486             f"cannot concatenate object of type '{type(obj)}'; "
    487             "only Series and DataFrame objs are valid"
    488         )
--> 489         raise TypeError(msg)
    491     ndims.add(obj.ndim)
    492 return ndims


TypeError: cannot concatenate object of type '<class 'list'>'; only Series and DataFrame objs are valid

import pandas as pd

from trase.tools.sps import SupplyChain

df = supplychain.get("flows")

# df.head()
# df_assets.head()
# df = df.groupby(["exporter_name"]).agg(sum)
# df = df.sort_values("vol_bean", ascending=False)
df = df[df["branch"] == "2.2.1"]
df = df[
    [
        "exporter_name",
        "customs_office.customs_office",
        "country_of_destination",
        "product_type",
        "vol_bean",
        "province.name",
    ]
]
df

import pandas as pd
import os

os.getcwd()
df = pd.read_csv(
    "/usr/share/TRASE/trase/models/argentina/soy/2018/results/results.csv", sep=";"
)
# df = df[df["LVL3_TRASE_ID_PROD"]== "AR-STOCK"]
df.head()

df = df.groupby(["BRANCH"]).agg(sum)
df = df.sort_values("VOLUME_TRADED", ascending=False)
df

# destined_for_quequen = df['ZONE_DESTINATION'] == 'QUEQUEN'
# origin_not_linked_to_quequen = ~df['ZONE_ORIGIN'].isin(['QUEQUEN', 'ZONA 3', 'ZONA 4'])
# should_exclude_quequen = destined_for_quequen & origin_not_linked_to_quequen
# df = df[~should_exclude_quequen]

# df[df['destination'] == "B BLANCA"]

Sankey

from trase.tools.sps import sankey

df = supplychain.get("flows")
sankey(
    df,
    "vol_bean",
    [
        "department_of_production.province.name",
        "exporter_name",
        "country_of_destination",
    ],
)

Chloropleth

from trase.tools.sps import consolidate, rename
from trase.tools.jupyter.observable import notebook

df = supplychain.get("flows")
df = df[df["exporter.cuit"] == "3350673744"].copy()  # NIDERA ARGENTINA
df = consolidate(df, ["vol_bean"], ["department_of_production.geocode"])
df = rename(df, {"department_of_production.geocode": "id", "vol_bean": "value"})
notebook(
    "@trase/choropleth-canvas",
    ["chart"],
    {"country": "argentina", "width": 1500, "data": df.to_dict("records")},
)