From 9ee3ef9d6b88760a8b22930e4a1ef210e741dfa8 Mon Sep 17 00:00:00 2001
From: Marcin Kostrzewski <komar86311@gmail.com>
Date: Fri, 1 Apr 2022 22:25:05 +0200
Subject: [PATCH] Dockerization

---
 Dockerfile                | 17 +++++++++++++++++
 power_plant_data_stats.py | 30 ++++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+)
 create mode 100644 Dockerfile
 create mode 100644 power_plant_data_stats.py

diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..58a8730
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,17 @@
+FROM python:3.9
+
+WORKDIR /app
+
+ADD ./requirements.txt .
+RUN pip install -r requirements.txt
+
+ADD . .
+ARG KAGGLE_USERNAME
+ARG KAGGLE_KEY
+ENV KAGGLE_USERNAME=${KAGGLE_USERNAME}
+ENV KAGGLE_KEY=${KAGGLE_KEY}
+
+RUN chmod u+x ./download_dataset.sh
+RUN ./download_dataset.sh
+
+CMD python power_plant_data_stats.py
diff --git a/power_plant_data_stats.py b/power_plant_data_stats.py
new file mode 100644
index 0000000..bc505b8
--- /dev/null
+++ b/power_plant_data_stats.py
@@ -0,0 +1,30 @@
+print('# statystyki dla pełnego zbioru')
+
+import pandas as pd
+plant_all = pd.read_csv('data/Plant_1_Generation_Data.csv')
+print(plant_all.describe(include='all'))
+
+print('# statystyki dla zbioru dev')
+
+plant_dev = pd.read_csv('data/Plant_1_Generation_Data.csv.dev')
+print(plant_dev.describe(include='all'))
+
+print('# statystyki dla zbioru test')
+
+plant_test = pd.read_csv('data/Plant_1_Generation_Data.csv.test')
+print(plant_test.describe(include='all'))
+
+print('# statystyki dla zbioru train')
+
+plant_train = pd.read_csv('data/Plant_1_Generation_Data.csv.train')
+print(plant_train.describe(include='all'))
+
+print('# normalizacja')
+
+
+plant_normalized = plant_test.copy()
+column = 'DC_POWER'
+
+plant_normalized[column] = plant_normalized[column]  / plant_normalized[column].abs().max()
+
+print(plant_normalized)
\ No newline at end of file