IUM_04 - add Dockerfile, fix download dataset script

Dockerfile

@@ -0,0 +1,20 @@
+# Base image
+FROM ubuntu:latest
+
+# Install python and pip
+RUN apt-get update && apt-get install -y \
+    python3 \
+    python3-pip
+
+# Install the required Python packages
+RUN pip3 install numpy pandas kaggle scikit-learn
+
+# Set the working directory
+WORKDIR /app
+
+# Copy scripts to the working directory
+COPY download_dataset.py ./
+COPY get_stats.py ./
+
+# Default command
+CMD bash

download_dataset.py

@@ -18,7 +18,7 @@ df = df.drop(columns=['Unnamed: 32'])
 # Check for CUTOFF parameter
 if len(sys.argv) > 1:
     CUTOFF = int(sys.argv[1])
-    df = df.iloc[:CUTOFF - 1]
+    df = df.iloc[:CUTOFF]
 
 # Check for missing values
 print(df.isnull().sum())