small fixes; seed settings and readme instructions

README.md

@@ -25,4 +25,4 @@ If running outside of docker, can do the following from root dir (where you can
 jupyter notebook --notebook-dir=$(pwd)
 ```
 
-Assuming all necessary things are installed.  Required Python packages are in `requirements.txt`, except for PyTorch.  Follow the installation instructions on the PyTorch website.  Also visit [dl4nlp.info](http://dl4nlp.info/en/latest/) for more information about the current training session and [nlproc.info](http://nlproc.info/) for more resources from us!
+Assuming all necessary things are installed.  Required Python packages are in `requirements.txt`, except for PyTorch. Also visit [dl4nlp.info](http://dl4nlp.info/en/latest/) for more information about the current training session and [nlproc.info](http://nlproc.info/) for more resources from us!

day_1/2_classify_names_with_MLP.ipynb

@@ -153,8 +153,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def fix_imbalance(df):\n",
-    "    #np.random.seed(seed)\n",
+    "def fix_imbalance(df, seed=0):\n",
+    "    np.random.seed(seed)\n",
     "    median = df.groupby('nationality').agg('count').split.median()\n",
     "    for nationality in df.nationality.unique():\n",
     "        \n",