Document existing classifiers

rosie/chamber_of_deputies/classifiers/election_expenses_classifier.py

@@ -5,6 +5,17 @@
 
 
 class ElectionExpensesClassifier(TransformerMixin):
+    """
+    Election Expenses classifier.
+
+    Check a `legal_entity` field for the presency of the political candidacy
+    category in the Brazilian Federal Revenue.
+
+    Dataset
+    -------
+    legal_entity : string column
+        Brazilian Federal Revenue category of companies, preceded by its code.
+    """
 
     def fit(self, X):
         return self

rosie/chamber_of_deputies/classifiers/irregular_companies_classifier.py

@@ -5,6 +5,24 @@
 
 
 class IrregularCompaniesClassifier(TransformerMixin):
+    """
+    Irregular Companies classifier.
+
+    Check for the official state of the company in the
+    Brazilian Federal Revenue and reports for rows with companies unauthorized
+    to sell products or services.
+
+    Dataset
+    -------
+    issue_date : datetime column
+        Date when the expense was made.
+
+    situation : string column
+        Situation of the company according to the Brazilian Federal Revenue.
+
+    situation_date : datetime column
+        Date when the situation was last updated.
+    """
 
     def fit(self, X):
         return self

rosie/chamber_of_deputies/classifiers/meal_price_outlier_classifier.py

@@ -7,7 +7,20 @@
 
 
 class MealPriceOutlierClassifier(TransformerMixin):
+    """
+    Meal Price Outlier classifier.
 
+    Dataset
+    -------
+    applicant_id : string column
+        A personal identifier code for every person making expenses.
+
+    net_value : float column
+        The value of the expense.
+
+    recipient_id : string column
+        A CNPJ (Brazilian company ID) or CPF (Brazilian personal tax ID).
+    """
 
     HOTEL_REGEX = r'hote(?:(?:ls?)|is)'
     CLUSTER_KEYS = ['mean', 'std']

rosie/chamber_of_deputies/classifiers/monthly_subquota_limit_classifier.py

@@ -6,6 +6,18 @@
 
 
 class MonthlySubquotaLimitClassifier(TransformerMixin):
+    """
+    Monthly Subquota Limit classifier.
+
+    Dataset
+    -------
+    issue_date : datetime column
+        Date when the expense was made.
+
+    net_value : float column
+        The value of the expense.
+    """
+
     KEYS = ['applicant_id', 'month', 'year']
 
     def fit(self, X):

rosie/chamber_of_deputies/classifiers/traveled_speeds_classifier.py

@@ -8,6 +8,31 @@
 
 
 class TraveledSpeedsClassifier(TransformerMixin):
+    """
+    Traveled Speeds classifier.
+
+    Dataset
+    -------
+    applicant_id : category column
+        A personal identifier code for every person making expenses.
+
+    category : category column
+        Category of the expense. The model will be applied just in rows where
+        the value is equal to "Meal".
+
+    is_party_expense : bool column
+        If the row corresponds to a party expense or not. The model will be
+        applied just in rows where the value is equal to `False`.
+
+    issue_date : datetime column
+        Date when the expense was made.
+
+    latitude : float column
+        Latitude of the place where the expense was made.
+
+    longitude : float column
+        Longitude of the place where the expense was made.
+    """
 
     AGG_KEYS = ['applicant_id', 'issue_date']
 

rosie/core/classifiers/invalid_cnpj_cpf_classifier.py

@@ -6,6 +6,20 @@
 
 
 class InvalidCnpjCpfClassifier(TransformerMixin):
+    """
+    Invalid CNPJ/CPF classifier.
+
+    Validate a `recipient_id` field by calculating its expected check digit
+    and verifying the authenticity of the provided ones.
+
+    Dataset
+    -------
+    document_type : category column
+        Validate rows with values 'bill_of_sale' or 'simple_receipt'.
+
+    recipient_id : string column
+        A CNPJ (Brazilian company ID) or CPF (Brazilian personal tax ID).
+    """
 
     def fit(self, X):
         return self
@@ -17,4 +31,5 @@ def predict(self, X):
         return np.r_[X.apply(self.__is_invalid, axis=1)]
 
     def __is_invalid(self, row):
-        return (row['document_type'] in ['bill_of_sale', 'simple_receipt']) & (not cpfcnpj.validate(str(row['recipient_id'])))
+        return (row['document_type'] in ['bill_of_sale', 'simple_receipt']) \
+            & (not cpfcnpj.validate(str(row['recipient_id'])))