added mission 9

Mission9Solutions.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
+   "execution_count": 136,
    "metadata": {
     "collapsed": false
    },
@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 82,
+   "execution_count": 137,
    "metadata": {
     "collapsed": false
    },
@@ -42,7 +42,7 @@
        " '1994,1,9,7,7910']"
       ]
      },
-     "execution_count": 82,
+     "execution_count": 137,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -60,23 +60,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 71,
+   "execution_count": 138,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
     "def read_csv(filename):\n",
-    "    data_string = open(filename).read()\n",
-    "    data_list = data_string.split(\"\\n\")[1:]\n",
-    "    final_list = list()\n",
+    "    string_data = open(filename).read()\n",
+    "    string_list = string_data.split(\"\\n\")[1:]\n",
+    "    final_list = []\n",
     "    \n",
-    "    for row in data_list:\n",
-    "        row_list = row.split(\",\")\n",
-    "        int_row_list = list()\n",
-    "        for val_string in row_list:\n",
-    "            int_row_list.append(int(val_string))\n",
-    "        final_list.append(int_row_list)\n",
+    "    for row in string_list:\n",
+    "        string_fields = row.split(\",\")\n",
+    "        int_fields = []\n",
+    "        for value in string_fields:\n",
+    "            int_fields.append(int(value))\n",
+    "        final_list.append(int_fields)\n",
     "    return final_list\n",
     "        \n",
     "cdc_list = read_csv(\"US_births_1994-2003_CDC_NCHS.csv\")"
@@ -84,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 85,
+   "execution_count": 139,
    "metadata": {
     "collapsed": false
    },
@@ -104,7 +104,7 @@
        " [1994, 1, 10, 1, 10498]]"
       ]
      },
-     "execution_count": 85,
+     "execution_count": 139,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -122,30 +122,46 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 73,
+   "execution_count": 140,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
+    "def read_csv(filename):\n",
+    "    string_data = open(filename).read()\n",
+    "    string_list = string_data.split(\"\\n\")[1:]\n",
+    "    final_list = []\n",
+    "    \n",
+    "    for row in string_list:\n",
+    "        string_fields = row.split(\",\")\n",
+    "        int_fields = []\n",
+    "        for value in string_fields:\n",
+    "            int_fields.append(int(value))\n",
+    "        final_list.append(int_fields)\n",
+    "    return final_list\n",
+    "        \n",
+    "cdc_list = read_csv(\"US_births_1994-2003_CDC_NCHS.csv\")\n",
+    "\n",
+    "\n",
     "def month_births(data):\n",
-    "    month_sums = dict()\n",
+    "    births_per_month = {}\n",
     "    \n",
     "    for row in data:\n",
     "        month = row[1]\n",
     "        births = row[4]\n",
-    "        if month in month_sums:\n",
-    "            month_sums[month] = month_sums[month] + births\n",
+    "        if month in births_per_month:\n",
+    "            births_per_month[month] = births_per_month[month] + births\n",
     "        else:\n",
-    "            month_sums[month] = births\n",
-    "    return month_sums\n",
+    "            births_per_month[month] = births\n",
+    "    return births_per_month\n",
     "    \n",
     "cdc_month_births = month_births(cdc_list)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 74,
+   "execution_count": 141,
    "metadata": {
     "collapsed": false
    },
@@ -167,7 +183,7 @@
        " 12: 3301860}"
       ]
      },
-     "execution_count": 74,
+     "execution_count": 141,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -185,32 +201,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 86,
+   "execution_count": 142,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
     "def dow_births(data):\n",
-    "    dow_sums = dict()\n",
+    "    births_per_dow = {}\n",
     "    \n",
     "    for row in data:\n",
     "        dow = row[3]\n",
     "        births = row[4]\n",
-    "        if dow in dow_sums:\n",
-    "            dow_sums[dow] = dow_sums[dow] + births\n",
+    "        if dow in births_per_dow:\n",
+    "            births_per_dow[dow] = births_per_dow[dow] + births\n",
     "        else:\n",
-    "            dow_sums[dow] = births\n",
-    "    return dow_sums\n",
+    "            births_per_dow[dow] = births\n",
+    "    return births_per_dow\n",
     "    \n",
     "cdc_dow_births = dow_births(cdc_list)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 87,
+   "execution_count": 143,
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "scrolled": true
    },
    "outputs": [
     {
@@ -225,7 +242,7 @@
        " 7: 4079723}"
       ]
      },
-     "execution_count": 87,
+     "execution_count": 143,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -243,17 +260,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 101,
+   "execution_count": 144,
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "def calc_counts(data, col_num):\n",
-    "    sums_dict = dict()\n",
+    "def calc_counts(data, column):\n",
+    "    sums_dict = {}\n",
     "    \n",
     "    for row in data:\n",
-    "        col_value = row[col_num]\n",
+    "        col_value = row[column]\n",
     "        births = row[4]\n",
     "        if col_value in sums_dict:\n",
     "            sums_dict[col_value] = sums_dict[col_value] + births\n",
@@ -269,7 +286,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 102,
+   "execution_count": 145,
    "metadata": {
     "collapsed": false
    },
@@ -289,7 +306,7 @@
        " 2003: 4089950}"
       ]
      },
-     "execution_count": 102,
+     "execution_count": 145,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -300,7 +317,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 146,
    "metadata": {
     "collapsed": false
    },
@@ -322,7 +339,7 @@
        " 12: 3301860}"
       ]
      },
-     "execution_count": 103,
+     "execution_count": 146,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -333,7 +350,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 147,
    "metadata": {
     "collapsed": false,
     "scrolled": true
@@ -375,7 +392,7 @@
        " 31: 746696}"
       ]
      },
-     "execution_count": 104,
+     "execution_count": 147,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -386,7 +403,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 148,
    "metadata": {
     "collapsed": false
    },
@@ -403,7 +420,7 @@
        " 7: 4079723}"
       ]
      },
-     "execution_count": 105,
+     "execution_count": 148,
      "metadata": {},
      "output_type": "execute_result"
     }

README.md

@@ -4,6 +4,7 @@ This repository is a series of notebooks that show solutions for the [projects](
 
 Of course, there are always going to be multiple ways to solve any one problem, so these notebooks just show one possible solution.
 
+- [Guided Project: Explore U.S. Births](https://github.com/dataquestio/solutions/blob/master/Mission9Solutions.ipynb)
 - [Guided Project: Customizing Data Visualizations](https://github.com/dataquestio/solutions/blob/master/Mission103Solutions.ipynb)
 - [Guided Project: Star Wars survey](https://github.com/dataquestio/solutions/blob/master/Mission201Solution.ipynb)
 - [Guided Project: Police killings](https://github.com/dataquestio/solutions/blob/master/Mission202Solution.ipynb)