PR changes requested by @henryre

.flake8

@@ -16,7 +16,7 @@ exclude =
     .mypy_cache,
     .tox,
     .env**,
-    .venv,
+    .venv**,
     _build,
     build,
     dist

intro/download_data.sh

@@ -1,9 +1,26 @@
-# Execute from snorkel-tutorials/spam/
-# Download data,
+#!/bin/bash
+set -euxo pipefail
 
+# Check that we are running from the right directory.
+if [ ! "${PWD##*/}" = "intro" ]; then
+    echo "Script must be run from intro directory" >&2
+    exit 1
+fi
+
+FILES=( "Youtube01-Psy.csv" "Youtube02-KatyPerry.csv" "Youtube03-LMFAO.csv" "Youtube04-Eminem.csv" "Youtube05-Shakira.csv" )
 DATA_URL="https://archive.ics.uci.edu/ml/machine-learning-databases/00380/YouTube-Spam-Collection-v1.zip"
+RELOAD=false
+
+# Check if at least any file is missing. If so, reload all data.
+for filename in "${FILES[@]}"
+do
+    if [ ! -e "data/$filename" ]; then
+        RELOAD=true
+    fi
+done
 
-if [ ! -d "data" ]; then
+if [ "$RELOAD" = true ]; then
+    if [ -d "data/" ]; then rm -Rf "data/"; fi
     mkdir -p data
     wget $DATA_URL -O data.zip
     mv data.zip data/
@@ -12,4 +29,4 @@ if [ ! -d "data" ]; then
     rm data.zip
     rm -rf __MACOSX
     cd ..
-fi
+fi