Change Dockerfile - python3 pip

Dockerfile

@@ -1,13 +1,19 @@
 FROM ubuntu:20.04
 
-COPY . /app
+RUN apt update >>/dev/null
+
+RUN apt install -y python3-pip >>/dev/null
 
 WORKDIR /app
 
-RUN pip install kaggle
+COPY . ./
-RUN pip install sklearn
-RUN pip install pandas
-RUN pip install seaborn
-RUN pip install matplotlib
 
-CMD ["run.sh"]
+RUN chmod +x run.sh
+
+RUN pip3 install kaggle
+RUN pip3 install sklearn
+RUN pip3 install pandas
+RUN pip3 install seaborn
+RUN pip3 install matplotlib
+
+CMD ./run.sh

ium_zadanie1.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3.7
 
 
 import pandas as pd
@@ -47,7 +46,7 @@ movies_subsets = pd.concat(movies_subsets, keys = ['Train','Test','Validation'])
 movies_subsets = movies_subsets.reset_index()
 ax = sns.boxplot(data = movies_subsets, x = 'level_0', y = 'rottentomatoes_audience_score')
 ax.set(title = 'Audience score distribution between subsets', ylabel = 'Audience score on Rotten Tomatoes', xlabel = 'SUBSET')
-plt.show(ax)
+#plt.show(ax)
 
 
 series.duration = series.duration.str.extract(r'(\d*)( seasons?)')[0].astype('int32')
@@ -75,4 +74,4 @@ series_subsets = pd.concat(series_subsets, keys = ['Train','Test','Validation'])
 series_subsets = series_subsets.reset_index()
 ax = sns.boxplot(data = series_subsets, x = 'level_0', y = 'rottentomatoes_audience_score')
 ax.set(title = 'Audience score distribution between subsets', ylabel = 'Audience score on Rotten Tomatoes', xlabel = 'SUBSET')
-plt.show(ax)
+#plt.show(ax)

run.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 kaggle kernels output 'eugenioscionti/scraping-rotten-tomatoes-to-enrich-netflix-dataset'
-python ium_zadanie1.py
+python3 ium_zadanie1.py