moved functions from py script to code cell

learn-co-curriculum · Jun 2, 2023 · 3b82cdd · 3b82cdd
1 parent 87c51ea
commit 3b82cdd
Show file tree

Hide file tree

Showing 2 changed files with 56 additions and 48 deletions.
diff --git a/flatiron_stats.py b/flatiron_stats.py
diff --git a/index.ipynb b/index.ipynb
@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -18,6 +19,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -27,6 +29,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -243,6 +246,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -471,7 +475,51 @@
    "outputs": [],
    "source": [
     "# __SOLUTION__ \n",
-    "import flatiron_stats as fs"
+    "import numpy as np\n",
+    "import scipy.stats as stats\n",
+    "\n",
+    "def welch_t(a, b):\n",
+    "    \n",
+    "    \"\"\" Calculate Welch's t statistic for two samples. \"\"\"\n",
+    "\n",
+    "    numerator = a.mean() - b.mean()\n",
+    "    \n",
+    "    # “ddof = Delta Degrees of Freedom”: the divisor used in the calculation is N - ddof, \n",
+    "    #  where N represents the number of elements. By default ddof is zero.\n",
+    "    \n",
+    "    denominator = np.sqrt(a.var(ddof=1)/a.size + b.var(ddof=1)/b.size)\n",
+    "    \n",
+    "    return np.abs(numerator/denominator)\n",
+    "\n",
+    "def welch_df(a, b):\n",
+    "    \n",
+    "    \"\"\" Calculate the effective degrees of freedom for two samples. This function returns the degrees of freedom \"\"\"\n",
+    "    \n",
+    "    s1 = a.var(ddof=1) \n",
+    "    s2 = b.var(ddof=1)\n",
+    "    n1 = a.size\n",
+    "    n2 = b.size\n",
+    "    \n",
+    "    numerator = (s1/n1 + s2/n2)**2\n",
+    "    denominator = (s1/ n1)**2/(n1 - 1) + (s2/ n2)**2/(n2 - 1)\n",
+    "    \n",
+    "    return numerator/denominator\n",
+    "\n",
+    "\n",
+    "def p_value_welch_ttest(a, b, two_sided=False):\n",
+    "    \"\"\"Calculates the p-value for Welch's t-test given two samples.\n",
+    "    By default, the returned p-value is for a one-sided t-test. \n",
+    "    Set the two-sided parameter to True if you wish to perform a two-sided t-test instead.\n",
+    "    \"\"\"\n",
+    "    t = welch_t(a, b)\n",
+    "    df = welch_df(a, b)\n",
+    "    \n",
+    "    p = 1-stats.t.cdf(np.abs(t), df)\n",
+    "    \n",
+    "    if two_sided:\n",
+    "        return 2*p\n",
+    "    else:\n",
+    "        return p"
    ]
   },
   {
@@ -492,10 +540,11 @@
    ],
    "source": [
     "# __SOLUTION__ \n",
-    "fs.p_value_welch_ttest(control.click, experiment.click)"
+    "p_value_welch_ttest(control.click, experiment.click)"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -514,6 +563,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -551,6 +601,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -610,6 +661,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -647,6 +699,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -670,6 +723,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [