Merge pull request #28 from ansg191/hypot3

Completes Hypothesis 3

1 files changed, 98 insertions, 30 deletions

diff --git a/CS105MiniProject.ipynb b/CS105MiniProject.ipynb
index 2bbfd79..3fc4eb7 100644
--- a/CS105MiniProject.ipynb
+++ b/CS105MiniProject.ipynb
@@ -31,8 +31,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:10.685764Z",
-     "start_time": "2024-02-24T06:19:10.663631Z"
+     "end_time": "2024-02-24T06:34:39.410627Z",
+     "start_time": "2024-02-24T06:34:39.389092Z"
     }
    },
    "outputs": [
@@ -79,8 +79,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:10.697650Z",
-     "start_time": "2024-02-24T06:19:10.686423Z"
+     "end_time": "2024-02-24T06:34:39.422395Z",
+     "start_time": "2024-02-24T06:34:39.411276Z"
     }
    },
    "outputs": [
@@ -140,8 +140,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:10.705920Z",
-     "start_time": "2024-02-24T06:19:10.699096Z"
+     "end_time": "2024-02-24T06:34:39.430868Z",
+     "start_time": "2024-02-24T06:34:39.423750Z"
     }
    },
    "outputs": [
@@ -170,8 +170,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:10.712944Z",
-     "start_time": "2024-02-24T06:19:10.706544Z"
+     "end_time": "2024-02-24T06:34:39.445408Z",
+     "start_time": "2024-02-24T06:34:39.434297Z"
     }
    },
    "outputs": [
@@ -206,8 +206,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:10.895599Z",
-     "start_time": "2024-02-24T06:19:10.713548Z"
+     "end_time": "2024-02-24T06:34:39.625934Z",
+     "start_time": "2024-02-24T06:34:39.447091Z"
     }
    },
    "outputs": [
@@ -277,8 +277,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:11.134307Z",
-     "start_time": "2024-02-24T06:19:10.902740Z"
+     "end_time": "2024-02-24T06:34:39.852958Z",
+     "start_time": "2024-02-24T06:34:39.628331Z"
     }
    },
    "id": "c533e52f7d64a4df",
@@ -320,8 +320,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:11.314257Z",
-     "start_time": "2024-02-24T06:19:11.136170Z"
+     "end_time": "2024-02-24T06:34:39.957772Z",
+     "start_time": "2024-02-24T06:34:39.855743Z"
     }
    },
    "id": "450665f2272bb3a2",
@@ -365,8 +365,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:11.453484Z",
-     "start_time": "2024-02-24T06:19:11.316819Z"
+     "end_time": "2024-02-24T06:34:40.102959Z",
+     "start_time": "2024-02-24T06:34:39.964444Z"
     }
    },
    "id": "1a704a4702ea3f9c",
@@ -411,8 +411,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:11.835916Z",
-     "start_time": "2024-02-24T06:19:11.455489Z"
+     "end_time": "2024-02-24T06:34:40.466605Z",
+     "start_time": "2024-02-24T06:34:40.108432Z"
     }
    },
    "id": "ae23070caa8a3c88",
@@ -467,8 +467,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:11.953795Z",
-     "start_time": "2024-02-24T06:19:11.836719Z"
+     "end_time": "2024-02-24T06:34:40.577484Z",
+     "start_time": "2024-02-24T06:34:40.487032Z"
     }
    },
    "id": "464b4dec962ea0ae",
@@ -516,8 +516,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:12.117410Z",
-     "start_time": "2024-02-24T06:19:11.957279Z"
+     "end_time": "2024-02-24T06:34:40.735256Z",
+     "start_time": "2024-02-24T06:34:40.578565Z"
     }
    },
    "id": "101f55892c052d46",
@@ -582,8 +582,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:12.131263Z",
-     "start_time": "2024-02-24T06:19:12.118937Z"
+     "end_time": "2024-02-24T06:34:40.749833Z",
+     "start_time": "2024-02-24T06:34:40.736572Z"
     }
    },
    "id": "24d1f01fdd4ca1d6",
@@ -618,8 +618,8 @@
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:12.135913Z",
-     "start_time": "2024-02-24T06:19:12.132121Z"
+     "end_time": "2024-02-24T06:34:40.753936Z",
+     "start_time": "2024-02-24T06:34:40.750695Z"
     }
    },
    "id": "fd3e73d9f461afd1",
@@ -639,18 +639,86 @@
    "id": "32eff09a99bfb3c7"
   },
   {
+   "cell_type": "markdown",
+   "source": [
+    "### Hypothesis 3: People who live with more people will have a higher GPA on average."
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "56a4b6a6c1e05d81"
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Average Household Size: 3.826923076923077\n",
+      "Average GPA: 3.6520247933884296\n",
+      "Pearson Correlation Coefficient: -0.2010052294084673\n"
+     ]
+    }
+   ],
+   "source": [
+    "hyp3_major_table = pd.crosstab(df.iloc[:, 5], df.iloc[:, 6], margins=True, margins_name='Total')\n",
+    "average_household_size = df.iloc[:, 5].mean(skipna=True)\n",
+    "average_gpa = df.iloc[:, 6].mean(skipna=True)\n",
+    "\n",
+    "print(\"Average Household Size:\", average_household_size)\n",
+    "print(\"Average GPA:\", average_gpa)\n",
+    "numerator = 0\n",
+    "denom_x = 0\n",
+    "denom_y = 0\n",
+    "for i in range(260):\n",
+    "    x_i = df.iloc[i, 5]\n",
+    "    y_i = df.iloc[i, 6]\n",
+    "    if not pd.isna(x_i) and not pd.isna(y_i):  # Check for NaN values\n",
+    "        numerator += (x_i - average_household_size) * (y_i - average_gpa)\n",
+    "        denom_x += (x_i - average_household_size)**2\n",
+    "        denom_y += (y_i - average_gpa)**2\n",
+    "\n",
+    "# Calculate Pearson correlation coefficient\n",
+    "pearson_coefficient = (numerator / ((denom_x * denom_y)**0.5))\n",
+    "print(\"Pearson Correlation Coefficient:\", pearson_coefficient)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-02-24T06:34:40.780079Z",
+     "start_time": "2024-02-24T06:34:40.755414Z"
+    }
+   },
+   "id": "b513f8e8241e86e5",
+   "execution_count": 14
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "With a Pearson Correlation Coefficient of -0.2, there is a slight negative correlation between household size and average GPA.\n",
+    "Students who live alone or with fewer people perform slightly better than those with more roommates.\n",
+    "\n",
+    "This goes against our hypothesis that people living with more people will have a higher GPA."
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "79b83b5ec3c1f9c5"
+  },
+  {
    "cell_type": "code",
    "outputs": [],
    "source": [],
    "metadata": {
     "collapsed": false,
     "ExecuteTime": {
-     "end_time": "2024-02-24T06:19:12.138622Z",
-     "start_time": "2024-02-24T06:19:12.136918Z"
+     "end_time": "2024-02-24T06:34:40.782502Z",
+     "start_time": "2024-02-24T06:34:40.780918Z"
     }
    },
-   "id": "b513f8e8241e86e5",
-   "execution_count": 13
+   "id": "55fb116c79c479a1",
+   "execution_count": 14
   }
  ],
  "metadata": {