Esempio n. 1
0
    def create_figures(self, items, items_dicts):
        jf = JsonFields(self.schema)
        tagged_fields = jf.tagged
        no_of_validated_items = len(items.df.index)

        dup_items_result = duplicate_rules.check_items(items.df, tagged_fields)
        no_of_checked_duplicated_items = dup_items_result.items_count
        no_of_duplicated_items = dup_items_result.err_items_count

        dup_skus_result = duplicate_rules.check_uniqueness(
            items.df, tagged_fields)
        no_of_checked_skus_items = dup_skus_result.items_count
        no_of_duplicated_skus = dup_skus_result.err_items_count

        price_was_now_result = price_rules.compare_was_now(
            items.df, tagged_fields)
        no_of_price_warns = price_was_now_result.err_items_count
        no_of_checked_price_items = price_was_now_result.items_count

        garbage_symbols_result = garbage_symbols(items)

        crawlera_user = api.get_crawlera_user(items.job)
        no_of_validation_warnings = self.report.results.get(
            "JSON Schema Validation").get_errors_count()
        quality_estimation, field_accuracy = generate_quality_estimation(
            items.job,
            crawlera_user,
            no_of_validation_warnings,
            no_of_duplicated_items,
            no_of_checked_duplicated_items,
            no_of_duplicated_skus,
            no_of_checked_skus_items,
            no_of_price_warns,
            no_of_validated_items,
            tested=True,
            garbage_symbols=garbage_symbols_result,
        )

        cleaned_df = self.drop_service_columns(items.df)

        self.score_table(quality_estimation, field_accuracy)
        self.job_summary_table(items.job)
        self.rules_summary_table(
            cleaned_df,
            no_of_validation_warnings,
            tagged_fields.get("name_field", ""),
            tagged_fields.get("product_url_field", ""),
            no_of_checked_duplicated_items,
            no_of_duplicated_items,
            tagged_fields.get("unique", []),
            no_of_checked_skus_items,
            no_of_duplicated_skus,
            tagged_fields.get("product_price_field", ""),
            tagged_fields.get("product_price_was_field", ""),
            no_of_checked_price_items,
            no_of_price_warns,
            garbage_symbols=garbage_symbols_result,
        )
        self.scraped_fields_coverage(items.job.key, cleaned_df)
        self.coverage_by_categories(cleaned_df, tagged_fields)
Esempio n. 2
0
 def run_customized_rules(self, items, tagged_fields):
     self.save_result(price_rules.compare_was_now(items.df, tagged_fields))
     self.save_result(
         duplicate_rules.check_uniqueness(items.df, tagged_fields))
     self.save_result(duplicate_rules.check_items(items.df, tagged_fields))
     self.save_result(
         category_rules.get_coverage_per_category(
             items.df, tagged_fields.get("category", [])))
Esempio n. 3
0
def test_check_uniqueness(data, tagged_fields, expected_messages,
                          expected_err_items_count):
    df = pd.DataFrame(data)
    assert check_uniqueness(df, tagged_fields) == create_result(
        "Uniqueness",
        expected_messages,
        items_count=len(df),
        err_items_count=expected_err_items_count,
    )
Esempio n. 4
0
    def create_figures(self, items):
        tagged_fields = Tags().get(self.schema)

        dup_items_result = duplicate_rules.check_items(items.df, tagged_fields)
        no_of_checked_duplicated_items = dup_items_result.items_count
        no_of_duplicated_items = dup_items_result.err_items_count

        dup_skus_result = duplicate_rules.check_uniqueness(
            items.df, tagged_fields)
        no_of_checked_skus_items = dup_skus_result.items_count
        no_of_duplicated_skus = dup_skus_result.err_items_count

        price_was_now_result = price_rules.compare_was_now(
            items.df, tagged_fields)
        no_of_price_warns = price_was_now_result.err_items_count
        no_of_checked_price_items = price_was_now_result.items_count

        crawlera_user = api.get_crawlera_user(items.job)

        validation_errors = self.report.results.get(
            "JSON Schema Validation",
            schema_rules.validate(self.schema, raw_items=items.raw,
                                  fast=False),
        ).get_errors_count()

        garbage_symbols_result = self.report.results.get(
            "Garbage Symbols", garbage_symbols(items))

        quality_estimation, field_accuracy = generate_quality_estimation(
            items.job,
            crawlera_user,
            validation_errors,
            no_of_duplicated_items,
            no_of_checked_duplicated_items,
            no_of_duplicated_skus,
            no_of_checked_skus_items,
            no_of_price_warns,
            no_of_checked_price_items,
            tested=True,
            garbage_symbols=garbage_symbols_result,
        )

        self.score_table(quality_estimation, field_accuracy)
        self.job_summary_table(items.job)
        self.rules_summary_table(
            items.df,
            validation_errors,
            tagged_fields.get("name_field", ""),
            tagged_fields.get("product_url_field", ""),
            no_of_checked_duplicated_items,
            no_of_duplicated_items,
            tagged_fields.get("unique", []),
            no_of_checked_skus_items,
            no_of_duplicated_skus,
            tagged_fields.get("product_price_field", ""),
            tagged_fields.get("product_price_was_field", ""),
            no_of_checked_price_items,
            no_of_price_warns,
            garbage_symbols=garbage_symbols_result,
        )
        self.scraped_fields_coverage(items.df)
        self.coverage_by_categories(items.df, tagged_fields)