fix script download

.gitignore

@@ -0,0 +1,2 @@
+/venv/
+/kaggle.json

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 ./

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")
+os.environ["KAGGLE_USERNAME"] = sys.argv[1]
-data = pd.read_csv("student-performance-multiple-linear-regression/Student_Performance.csv")
+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})

requirements.txt

@@ -0,0 +1,3 @@
+kaggle
+pandas
+scikit-learn