From 7183a7947e2e9a64c6f9302410885eeedb60f90e Mon Sep 17 00:00:00 2001
From: murilo <murilobellatini@gmail.com>
Date: Sun, 6 Sep 2020 21:36:07 -0300
Subject: [PATCH] Fix sensitive data columns

---
 .../04-create-trusted-data-order-Copy1.ipynb  |  10 +++++-----
 dev/docker-volume/src/DataProcessor.py        |   2 +-
 .../__pycache__/DataProcessor.cpython-38.pyc  | Bin 4302 -> 4281 bytes
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/dev/docker-volume/notebooks/04-create-trusted-data-order-Copy1.ipynb b/dev/docker-volume/notebooks/04-create-trusted-data-order-Copy1.ipynb
index 0f4b24d..1bf1515 100644
--- a/dev/docker-volume/notebooks/04-create-trusted-data-order-Copy1.ipynb
+++ b/dev/docker-volume/notebooks/04-create-trusted-data-order-Copy1.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [
     {
@@ -24,7 +24,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
@@ -61,7 +61,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
@@ -70,7 +70,7 @@
        "pyspark.sql.session.SparkSession"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 34,
      "metadata": {},
      "output_type": "execute_result"
     }
diff --git a/dev/docker-volume/src/DataProcessor.py b/dev/docker-volume/src/DataProcessor.py
index 48b9f38..dc48e14 100644
--- a/dev/docker-volume/src/DataProcessor.py
+++ b/dev/docker-volume/src/DataProcessor.py
@@ -123,7 +123,7 @@ def create_trusted_order(spark:SparkSession):
     output_path = TRUSTED_DATA_PATH / 'order'
 
     # anonymize sensitive data by dropping columns
-    sensitive_data_columns = ['cpf', 'customer_name', 'consumer_customer_name', 'consumer_customer_phone_number']
+    sensitive_data_columns = ['order_cpf', 'order_customer_name', 'consumer_customer_name', 'consumer_customer_phone_number']
     tmp = tmp.drop(*sensitive_data_columns)
 
     tmp.write.parquet(str(output_path))
diff --git a/dev/docker-volume/src/__pycache__/DataProcessor.cpython-38.pyc b/dev/docker-volume/src/__pycache__/DataProcessor.cpython-38.pyc
index fbcb3a0556ca9cc3f073cfba2f6ab1364f082758..2847d51ce954e314c5fbfc947975ab873c607b93 100644
GIT binary patch
delta 100
zcmX@7xKoigl$V!_0SJN`LgQUG^7imBPMbW7r**PEZ<25nXMRyiYEgW0L0XhBggJQz
yZvZ3P<d?kilg0V684V^k^BJ(R2rv~DPTs{gjjaf1Qc>~dFn$e2#=^<<0{#He6CGFp

delta 120
zcmdm~cutWwl$V!_0SHdihsK+4<n7^MTsC<YPpd!;YZluA_7aX7wr0kKjEoGE<$06X
zi?o0$Z}Co^!W+QIIr%BCJWr7qP^8EeM7T|6<jZ3;nq0tVz|JH9ghfS@m-0<xD+WoH
QY<A?=U}P+soF(8707MTR=>Px#