From 00b57384c2da1d071a407c801bf50c3d16334a06 Mon Sep 17 00:00:00 2001
From: Sheaza <nataliawolowiec3@gmail.com>
Date: Tue, 2 Apr 2024 19:43:25 +0200
Subject: [PATCH] fix script download

---
 .gitignore                         |  2 ++
 Dockerfile                         | 13 +++++++++++++
 get_dataset.py                     | 11 ++++++++---
 stats/get_stats.py => get_stats.py |  0
 requirements.txt                   |  3 +++
 5 files changed, 26 insertions(+), 3 deletions(-)
 create mode 100644 .gitignore
 create mode 100644 Dockerfile
 rename stats/get_stats.py => get_stats.py (100%)
 create mode 100644 requirements.txt

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..915cc65
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+/venv/
+/kaggle.json
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..e0c8dfb
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,13 @@
+FROM python:3.11
+
+RUN apt-get update && apt-get -y upgrade
+RUN apt-get install -y build-essential
+
+RUN python -m pip install --upgrade pip
+COPY requirements.txt /tmp
+RUN python -m pip install -r /tmp/requirements.txt
+
+WORKDIR ./app
+
+COPY ./get_dataset.py ./
+COPY ./get_stats.py ./
diff --git a/get_dataset.py b/get_dataset.py
index 0543413..61cb483 100644
--- a/get_dataset.py
+++ b/get_dataset.py
@@ -1,10 +1,15 @@
-import opendatasets as od
 import pandas as pd
 from sklearn import preprocessing
 from sklearn.model_selection import train_test_split
+import sys
+import os
 
-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")
+os.environ["KAGGLE_USERNAME"] = sys.argv[1]
+os.environ["KAGGLE_KEY"] = sys.argv[2]
+
+os.system("kaggle datasets download -d nikhil7280/student-performance-multiple-linear-regression --unzip")
+
+data = pd.read_csv("Student_Performance.csv")
 print(data.head())
 data.drop_duplicates(inplace=True)
 data["Extracurricular Activities"] = data["Extracurricular Activities"].replace({'Yes': 1, 'No': 0})
diff --git a/stats/get_stats.py b/get_stats.py
similarity index 100%
rename from stats/get_stats.py
rename to get_stats.py
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..fef1509
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,3 @@
+kaggle
+pandas
+scikit-learn
\ No newline at end of file