Update to use rur and urb keys for doctors loc column

minireference · Mar 29, 2024 · 16472d7 · 16472d7
1 parent 689b1e8
commit 16472d7
Show file tree

Hide file tree

Showing 7 changed files with 153 additions and 224 deletions.
diff --git a/exercises/exercises_31_estimtors.ipynb b/exercises/exercises_31_estimtors.ipynb
@@ -229,11 +229,11 @@
     "### Exercise 3.3\n",
     "\n",
     "Compute the difference between the means of the sleep `score` s \n",
-    "for the doctors working in `rural` locations and `urban` locations\n",
+    "for the doctors working in `rur`al locations and `urb`an locations\n",
     "in the doctors dataset `datasets/doctors.csv` .\n",
     "\n",
-    "Hint: Use the code `doctors[doctors[\"location\"]==\"rural\"]` to select\n",
-    "the subset of the doctors working in a `rural` location."
+    "Hint: Use the code `doctors[doctors[\"loc\"]==\"rur\"]` to select\n",
+    "the subset of the doctors working in a rural location."
    ]
   },
   {
@@ -244,8 +244,8 @@
    "outputs": [],
    "source": [
     "doctors = pd.read_csv(\"datasets/doctors.csv\")\n",
-    "scoresR = doctors[doctors[\"location\"]==\"rural\"][\"score\"]\n",
-    "scoresU = ... # select doctors from \"urban\" location here...\n",
+    "scoresR = doctors[doctors[\"loc\"]==\"rur\"][\"score\"]\n",
+    "scoresU = ... # select doctors from \"urb\" location here...\n",
     "\n",
     "# compute difference between scores"
    ]
@@ -777,8 +777,8 @@
     "\n",
     "Describe the uncertainty about the difference between means `dmeans(scoresR,scoresU)` ,\n",
     "where `scoresR` and `scoresU` are sleep scores of the rural and urban doctors\n",
-    "from the doctors dataset `datasets/apples.csv` .  \n",
-    "**a)** Find an analytical formula in terms Student's $t$ -distribution.  \n",
+    "from the doctors dataset `datasets/doctors.csv` .  \n",
+    "**a)** Find an analytical formula in terms Student's $t$-distribution.  \n",
     "**b)** Use bootstrap estimation.  \n",
     "**c)** Compare your answers from part a) and b) graphically."
    ]
@@ -802,7 +802,7 @@
    ],
    "source": [
     "doctors = pd.read_csv(\"datasets/doctors.csv\")\n",
-    "scoresR = doctors[doctors[\"location\"]==\"rural\"][\"score\"]\n",
+    "scoresR = doctors[doctors[\"loc\"]==\"rur\"][\"score\"]\n",
     "scoresU = ... # select urban doctors ...\n",
     "\n",
     "# observed difference\n",
@@ -1025,7 +1025,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 36,
    "id": "7a1f9847-c46d-4d91-81d4-f4f0b41b4828",
    "metadata": {},
    "outputs": [
@@ -1035,7 +1035,7 @@
        "Ellipsis"
       ]
      },
-     "execution_count": 40,
+     "execution_count": 36,
      "metadata": {},
      "output_type": "execute_result"
     }

diff --git a/exercises/exercises_32_confidence_intervals.ipynb b/exercises/exercises_32_confidence_intervals.ipynb
@@ -282,8 +282,8 @@
    "id": "4b35dd4e-4a8c-498e-8a14-c216b04b4367",
    "metadata": {},
    "source": [
-    "Hint: Use the code `doctors[doctors[\"location\"]==\"rural\"]` to select\n",
-    "the subset of the doctors working in a `rural` location."
+    "Hint: Use the code `doctors[doctors[\"loc\"]==\"rur\"]` to select\n",
+    "the subset of the doctors working in a `rur`al location."
    ]
   },
   {
@@ -294,8 +294,8 @@
    "outputs": [],
    "source": [
     "doctors = pd.read_csv(\"datasets/doctors.csv\")\n",
-    "scoresR = doctors[doctors[\"location\"]==\"rural\"][\"score\"]\n",
-    "scoresU = doctors[doctors[\"location\"]==\"urban\"][\"score\"]\n",
+    "scoresR = doctors[doctors[\"loc\"]==\"rur\"][\"score\"]\n",
+    "scoresU = doctors[doctors[\"loc\"]==\"urb\"][\"score\"]\n",
     "\n",
     "# observed difference between scores\n",
     "dscores = ..."

diff --git a/exercises/exercises_35_two_sample_tests.ipynb b/exercises/exercises_35_two_sample_tests.ipynb
@@ -111,7 +111,7 @@
     {
      "data": {
       "text/plain": [
-       "2.2236048265460084"
+       "6.992885375494076"
       ]
      },
      "execution_count": 3,
@@ -121,8 +121,8 @@
    ],
    "source": [
     "doctors = pd.read_csv(\"../datasets/doctors.csv\")\n",
-    "scoresU = doctors[doctors[\"location\"]==\"urban\"][\"score\"]\n",
-    "scoresR = doctors[doctors[\"location\"]==\"rural\"][\"score\"]\n",
+    "scoresU = doctors[doctors[\"loc\"]==\"urb\"][\"score\"]\n",
+    "scoresR = doctors[doctors[\"loc\"]==\"rur\"][\"score\"]\n",
     "\n",
     "# observed difference between means\n",
     "dhat = dmeans(scoresR, scoresU)\n",
@@ -138,7 +138,7 @@
     {
      "data": {
       "text/plain": [
-       "0.0122"
+       "0.0496"
       ]
      },
      "execution_count": 4,
@@ -161,7 +161,7 @@
     {
      "data": {
       "text/plain": [
-       "0.0122987701229877"
+       "0.05019498050194981"
       ]
      },
      "execution_count": 5,

diff --git a/exercises/solutions/exercises_31_estimtors.ipynb b/exercises/solutions/exercises_31_estimtors.ipynb
diff --git a/exercises/solutions/exercises_32_confidence_intervals.ipynb b/exercises/solutions/exercises_32_confidence_intervals.ipynb
@@ -299,8 +299,8 @@
    "id": "4b35dd4e-4a8c-498e-8a14-c216b04b4367",
    "metadata": {},
    "source": [
-    "Hint: Use the code `doctors[doctors[\"location\"]==\"rural\"]` to select\n",
-    "the subset of the doctors working in a `rural` location."
+    "Hint: Use the code `doctors[doctors[\"loc\"]==\"rur\"]` to select\n",
+    "the subset of the doctors working in a rural location."
    ]
   },
   {
@@ -312,7 +312,7 @@
     {
      "data": {
       "text/plain": [
-       "2.2236048265460084"
+       "6.992885375494076"
       ]
      },
      "execution_count": 9,
@@ -322,8 +322,8 @@
    ],
    "source": [
     "doctors = pd.read_csv(\"datasets/doctors.csv\")\n",
-    "scoresR = doctors[doctors[\"location\"]==\"rural\"][\"score\"]\n",
-    "scoresU = doctors[doctors[\"location\"]==\"urban\"][\"score\"]\n",
+    "scoresR = doctors[doctors[\"loc\"]==\"rur\"][\"score\"]\n",
+    "scoresU = doctors[doctors[\"loc\"]==\"urb\"][\"score\"]\n",
     "\n",
     "# observed difference between scores\n",
     "dscores = dmeans(scoresR,scoresU)\n",
@@ -347,7 +347,7 @@
     {
      "data": {
       "text/plain": [
-       "[0.48541688303387676, 3.96179277005814]"
+       "[-0.10091805996217662, 14.086688810950328]"
       ]
      },
      "execution_count": 10,
@@ -384,7 +384,7 @@
     {
      "data": {
       "text/plain": [
-       "[0.48541688303387676, 3.96179277005814]"
+       "[-0.10091805996217662, 14.086688810950328]"
       ]
      },
      "execution_count": 11,
@@ -415,7 +415,7 @@
     {
      "data": {
       "text/plain": [
-       "[0.5319758672699874, 3.9718042986425353]"
+       "[0.09320158102766672, 13.803270750988135]"
       ]
      },
      "execution_count": 12,