Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Task: Numeric and Datetime Errors #415 #426

Merged
merged 2 commits into from
Jan 6, 2025
Merged

Task: Numeric and Datetime Errors #415 #426

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0855ac2
Fixing type error checking
JulianForeman Dec 11, 2024
432c580
Removing import variable casting and redundant try except block
JulianForeman Jan 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
96 changes: 43 additions & 53 deletions django/api/services/spreadsheet_uploader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
import traceback
import numpy as np
from django.db import transaction
from datetime import datetime
from datetime import datetime, date

def get_field_default(model, field):
field = model._meta.get_field(field)
Expand Down Expand Up @@ -52,10 +52,10 @@ def transform_data(
errors_and_warnings = {}

missing_columns = [col for col in required_columns if col not in df.columns]
if (missing_columns):
if missing_columns:
errors_and_warnings['Headers'] = {}
errors_and_warnings['Headers']['Missing Headers'] = {
"Expected Type": "missing one or more required columns",
"Expected Type": "Missing one or more required columns",
"Rows": missing_columns,
"Severity": "Critical"
}
Expand All @@ -73,7 +73,7 @@ def transform_data(
float: "Float",
Decimal: "Decimal",
str: "String",
datetime: "Date (YYYY-MM-DD)"
datetime.date: "Date (YYYY-MM-DD)"
}

df = df.replace({np.nan: None})
Expand All @@ -86,7 +86,7 @@ def transform_data(

if db_field_name:
is_nullable = db_field_name in nullable_fields
expected_type = field_types.get(column)
expected_type = field_types.get(db_field_name)

if pd.isna(value) or value == "" or value is None:
if is_nullable:
Expand All @@ -101,52 +101,42 @@ def transform_data(
"Severity": "Error"
}
errors_and_warnings[column]["Empty Value"]["Rows"].append(index + 1)

if expected_type == datetime and value is not None and value != '':
try:
datetime.strptime(value, "%Y-%m-%d")
except ValueError:
if column not in errors_and_warnings:
errors_and_warnings[column] = {}
if "Incorrect Date Format" not in errors_and_warnings[column]:
errors_and_warnings[column]["Incorrect Date Format"] = {
"Expected Type": "The following rows contained an incorrect date format. Expected YYYY-MM-DD.",
"Rows": [],
"Severity": "Error"
}
errors_and_warnings[column]["Incorrect Date Format"]["Rows"].append(index + 1)

if expected_type in [int, float, Decimal] and value is not None and pd.notna(value) and value != '':
value = str(value).replace(',', '').strip()
try:
if expected_type == int:
row_dict[column] = int(float(value))
elif expected_type == Decimal:
row_dict[column] = Decimal(value).quantize(Decimal("0.01"), rounding=ROUND_HALF_UP)
else:
row_dict[column] = float(value)
except ValueError:
if column not in errors_and_warnings:
errors_and_warnings[column] = {}
if "Incorrect Type" not in errors_and_warnings[column]:
errors_and_warnings[column]["Incorrect Type"] = {
"Expected Type": f"The following rows contained types for the column {column}. Expected {type_to_string.get(expected_type, str(expected_type))}",
"Rows": [],
"Severity": "Error"
}
errors_and_warnings[column]["Incorrect Type"]["Rows"].append(index + 1)

# Check if expected_type is valid before using isinstance
elif expected_type is not None and isinstance(expected_type, type) and not isinstance(row_dict[column], expected_type) and value != "":
if column not in errors_and_warnings:
errors_and_warnings[column] = {}
if "Incorrect Type" not in errors_and_warnings[column]:
errors_and_warnings[column]["Incorrect Type"] = {
"Expected Type": f"The following rows contained types for the column {column}. Expected {type_to_string.get(expected_type, str(expected_type))}",
"Rows": [],
"Severity": "Error"
}
errors_and_warnings[column]["Incorrect Type"]["Rows"].append(index + 1)
else:
if expected_type:
try:
if expected_type == int:
row_dict[column] = int(float(value))
elif expected_type == float:
row_dict[column] = float(value)
elif expected_type == Decimal:
row_dict[column] = Decimal(value).quantize(
Decimal("0.01"), rounding=ROUND_HALF_UP
)
elif expected_type == date:
if isinstance(value, datetime):
parsed_date = value.date()
else:
parsed_date = datetime.strptime(value, "%Y-%m-%d").date()
row_dict[column] = parsed_date
elif expected_type == str and type(value) == bool:
row_dict[column] = str(value)
except (ValueError, TypeError):
if column not in errors_and_warnings:
errors_and_warnings[column] = {}
if "Incorrect Type" not in errors_and_warnings[column]:
if expected_type == date:
errors_and_warnings[column]["Incorrect Type"] = {
"Expected Type": "Date in the format YYYY-MM-DD",
"Rows": [],
"Severity": "Error"
}
else:
errors_and_warnings[column]["Incorrect Type"] = {
"Expected Type": f"Expected {type_to_string.get(expected_type, str(expected_type))}",
"Rows": [],
"Severity": "Error"
}
errors_and_warnings[column]["Incorrect Type"]["Rows"].append(index + 1)

for x in validation_functions:
validate = x["function"]
Expand All @@ -160,7 +150,7 @@ def transform_data(
errors_and_warnings[column] = {}
for issue, details in issues.items():
if issue not in errors_and_warnings[column]:
if(details.get("Severity", "Error") == 'Warning'):
if details.get("Severity", "Error") == 'Warning':
errors_and_warnings[column][issue] = {
"Expected Type": details.get("Expected Type", "Unknown"),
"Groups": details.get("Groups", []),
Expand All @@ -170,7 +160,7 @@ def transform_data(
errors_and_warnings[column][issue] = {
"Expected Type": details.get("Expected Type", "Unknown"),
"Rows": details.get("Rows", []),
"Severity": details.get("Severity", "Error")
"Severity": "Error"
}
else:
errors_and_warnings[column][issue]["Groups"].extend(details.get("Groups", []))
Expand Down
Loading