From 76154a9157a71bada3a48d260e5d3759982fc63d Mon Sep 17 00:00:00 2001
From: Sheaza <nataliawolowiec3@gmail.com>
Date: Tue, 2 Apr 2024 18:31:57 +0200
Subject: [PATCH] create python scripts for stats and downloading dataset

---
 get_dataset.py     | 18 ++++++++++++++++++
 stats/get_stats.py | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 get_dataset.py
 create mode 100644 stats/get_stats.py

diff --git a/get_dataset.py b/get_dataset.py
new file mode 100644
index 0000000..0543413
--- /dev/null
+++ b/get_dataset.py
@@ -0,0 +1,18 @@
+import opendatasets as od
+import pandas as pd
+from sklearn import preprocessing
+from sklearn.model_selection import train_test_split
+
+od.download("https://www.kaggle.com/datasets/nikhil7280/student-performance-multiple-linear-regression/code")
+data = pd.read_csv("student-performance-multiple-linear-regression/Student_Performance.csv")
+print(data.head())
+data.drop_duplicates(inplace=True)
+data["Extracurricular Activities"] = data["Extracurricular Activities"].replace({'Yes': 1, 'No': 0})
+
+data[data.columns[:-1]] = preprocessing.StandardScaler().fit_transform(data[data.columns[:-1]])
+print(data.head())
+df_train, df_test = train_test_split(data, test_size=0.2, random_state=21, shuffle=True)
+data.to_csv("dataset.csv", index=False)
+df_train.to_csv("df_train.csv", index=False)
+df_test.to_csv("df_test.csv", index=False)
+
diff --git a/stats/get_stats.py b/stats/get_stats.py
new file mode 100644
index 0000000..43fba39
--- /dev/null
+++ b/stats/get_stats.py
@@ -0,0 +1,34 @@
+import pandas as pd
+
+
+pd.set_option('display.max_columns', None)
+pd.set_option('display.max_rows', None)
+
+
+df = pd.read_csv('./dataset.csv')
+df_train = pd.read_csv('./df_train.csv')
+df_test = pd.read_csv('./df_test.csv')
+
+
+with open('stats.txt', 'w') as f:
+    f.write(f"Wielkość całego zbioru:\n {df.shape}\n")
+    f.write(f"Wielkość treningowego zbioru:\n {df_train.shape}\n")
+    f.write(f"Wielkość testowego zbioru:\n {df_test.shape}\n")
+
+    f.write(f"\nStatystyki dla całego zbioru:\n")
+    f.write(f"{df.describe()}\n")
+
+    f.write(f"\nStatystyki dla treningowego zbioru:\n")
+    f.write(f"{df_train.describe()}\n")
+
+    f.write(f"\nStatystyki dla testowego zbioru:\n")
+    f.write(f"{df_test.describe()}\n")
+
+    f.write(f"\nRozkład zmiennej wyjściowej dla całości:\n")
+    f.write(f"{df['Performance Index'].value_counts()}\n")
+
+    f.write(f"\nRozkład zmiennej wyjściowej dla zbioru treningowego:\n")
+    f.write(f"{df_train['Performance Index'].value_counts()}\n")
+
+    f.write(f"\nRozkład zmiennej wyjściowej dla zbioru testowego:\n")
+    f.write(f"{df_test['Performance Index'].value_counts()}\n")
\ No newline at end of file