From a70a6ebc9620f763fc22de8c0bc4c0a682c67051 Mon Sep 17 00:00:00 2001
From: Jakub Henyk <jakhen@st.amu.edu.pl>
Date: Tue, 4 Apr 2023 13:58:30 +0200
Subject: [PATCH] changed .ipynb to .py

---
 Dockerfile  |  6 +++---
 zadanie1.py | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+), 3 deletions(-)
 create mode 100644 zadanie1.py

diff --git a/Dockerfile b/Dockerfile
index 9c26b8b..5f900ab 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -11,8 +11,8 @@ RUN apt-get install -y python3
 RUN apt-get install -y python3-pip
 RUN python3 -m pip install pandas
 
-COPY ./zadanie1.ipynb ./
+COPY ./zadanie1.py ./
 
-RUN chmod +x ./zadanie1.ipynb
+RUN chmod +x ./zadanie1.py
 
-CMD ./zadanie1.ipynb
\ No newline at end of file
+CMD ./zadanie1.py
\ No newline at end of file
diff --git a/zadanie1.py b/zadanie1.py
new file mode 100644
index 0000000..7bfd817
--- /dev/null
+++ b/zadanie1.py
@@ -0,0 +1,34 @@
+import pandas as pd
+import numpy as np
+
+data = pd.read_csv("Customers.csv")
+print(data[:10])
+
+dataF = data
+
+mapping = {'NaN' : 0, 'Healthcare' : 1, 'Engineer' : 2, 'Lawyer' : 3, 'Entertainment' : 4, 'Artist' : 5, 'Executive' : 6,
+ 'Doctor' : 7, 'Homemaker' : 8, 'Marketing' : 9}
+
+mapping2 = {'Male' : 0, 'Female' : 1}
+
+dataF = dataF.replace({'Profession': mapping})
+dataF = dataF.replace({'Gender': mapping2})
+
+dataF = dataF.drop(columns=['CustomerID'])
+
+dataF['Profession'] = dataF['Profession'].fillna(0)
+
+normalized_dataF = (dataF - dataF.min())/(dataF.max() - dataF.min())
+
+print(normalized_dataF[:10])
+
+train_data = normalized_dataF[0:1600]
+dev_data = normalized_dataF[1600:1800]
+test_data = normalized_dataF[1800:]
+
+print(f"Wielkość zbioru Customers: {len(data)} elementów")
+print(f"Wielkość zbioru trenującego: {len(train_data)} elementów")
+print(f"Wielkość zbioru walidującego: {len(dev_data)} elementów")
+print(f"Wielkość zbioru testującego: {len(test_data)} elementów")
+
+print(f" \nDane i wartości na temat zbioru: \n \n {normalized_dataF.describe()}")