update part 3

Author: emilygrabowski

lessons/Part3/13_Numpy.ipynb

@@ -462,7 +462,9 @@
   {
    "cell_type": "code",
    "execution_count": 77,
-   "metadata": {},
+   "metadata": {
+    "scrolled": true
+   },
    "outputs": [
     {
      "data": {
@@ -479,6 +481,23 @@
    "source": [
     "np.array(converted_df)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Challenge: operation in numpy to manipulate array with a couple of different functions \n",
+    "\n",
+    "## 1) indexing\n",
+    "##) reshaping\n",
+    "\n",
+    "## argsort/argwhere for arrays\n",
+    "\n",
+    "\n",
+    "## initialize arrays and fill in values (preallocation)"
+   ]
   }
  ],
  "metadata": {

lessons/Part3/14_Statsmodels.ipynb

@@ -137,7 +137,8 @@
     "\n",
     "Choose one of the following options: \n",
     "\n",
-    "1. Use a t-test or linear regression on another combination of variables (e.g. predict flipper_length)\n",
+    "1. Use a t-test or linear regression on another combination of variables (e.g. predict flipper_length) \n",
+    "2. Pairwise ttest  / logistic regression / wilcoxan test? \n",
     "\n",
     "2. From the [documentation](https://www.statsmodels.org/dev/api.html) choose another model or test (consider those you might use in your work) and apply it to the penguins dataset. \n",
     "\n",

lessons/Part4/017_Project.ipynb renamed to lessons/Part4/17_Project.ipynb

@@ -20,7 +20,8 @@
    "source": [
     "## Introducing the Dataset\n",
     "\n",
-    "- Find a bunch of text files\n"
+    "- airline tweet dataset\n",
+    "\n"
    ]
   },
   {
@@ -30,9 +31,9 @@
     "## Import data:\n",
     "\n",
     "Skills to include: \n",
-    "- import multiple files in a directory, (with some simple parsing funtions)\n",
+    "- import multiple files in a directory, (with some simple parsing funtions) (for-loop, if statement to filter for the relevant files)\n",
     "- combine them into a single dataframe (pd.concat)\n",
-    "- write a function called parse_files\n"
+    "- combine into parse files function\n"
    ]
   },
   {
@@ -44,15 +45,19 @@
     "Skills:\n",
     "- Subsetting a dataframe\n",
     "- Modifying a column\n",
-    "- "
+    "- numpy \n",
+    "- feature engineering \n",
+    "- introduce a new package (string processing)\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "## One statistical model \n",
-    "your choice\n",
+    "\n",
+    "linear regression on retweets? \n",
+    "\n",
     "\n"
    ]
   },
@@ -61,8 +66,16 @@
    "metadata": {},
    "source": [
     "## One visualization\n",
-    "your choice"
+    "\n",
+    "date time? "
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {