s444409/Bootstrap-t-student
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

fixes

Browse Source
This commit is contained in:
test 2022-05-17 16:21:32 +02:00
parent 0dea9ae3fd
commit 176f10fde6
1 changed files with 61 additions and 81 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

140
bootstrap-t.ipynb
View File

@ -28,7 +28,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 155,
"outputs": [], "outputs": [],
"source": [ "source": [
"# TODO: Poprzestawiać kolejność definicji funkcji?" "# TODO: Poprzestawiać kolejność definicji funkcji?"
@ -42,7 +42,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 252, "execution_count": 156,
"metadata": { "metadata": {
"pycharm": { "pycharm": {
"name": "#%%\n" "name": "#%%\n"
@ -62,7 +62,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 253, "execution_count": 157,
"metadata": { "metadata": {
"pycharm": { "pycharm": {
"name": "#%%\n" "name": "#%%\n"
@ -79,7 +79,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 254, "execution_count": 158,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -88,19 +88,18 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def t_stat_single(sample, population_mean=2):\n", "def t_stat_single(sample, population_mean):\n",
" # TODO: Wywalić min, funkcja nie powinna działać dla pustej próbki\n",
" # TODO: population mean nie powinien mieć defaultowego argumentu\n",
" \"\"\"Funkcja oblicza wartość statystyki testowej dla jednej próbki\"\"\"\n", " \"\"\"Funkcja oblicza wartość statystyki testowej dla jednej próbki\"\"\"\n",
" if sample.empty:\n",
" raise Exception(\"Empty sample\")\n",
" sample = sample[0].values.tolist()\n", " sample = sample[0].values.tolist()\n",
" sample_size = len(sample)\n", " sample_size = len(sample)\n",
" # min is to fix near-zero values causing zero division erros\n", " return (mean(sample) - population_mean) / (stdev(sample) / sqrt(sample_size))"
" return (mean(sample) - population_mean) / (stdev(sample) / min(0.00000001, sqrt(sample_size)))"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 255, "execution_count": 159,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -111,6 +110,8 @@
"source": [ "source": [
"def t_stat_ind(sample_1, sample_2):\n", "def t_stat_ind(sample_1, sample_2):\n",
" \"\"\"Funkcja oblicza wartość statystyki testowej dla dwóch próbek niezależnych\"\"\"\n", " \"\"\"Funkcja oblicza wartość statystyki testowej dla dwóch próbek niezależnych\"\"\"\n",
" if sample_1.empty or sample_2.empty:\n",
" raise Exception(\"Empty sample\")\n",
" sample_1 = sample_1[0].values.tolist()\n", " sample_1 = sample_1[0].values.tolist()\n",
" sample_2 = sample_2[0].values.tolist()\n", " sample_2 = sample_2[0].values.tolist()\n",
" sed = sqrt(sem(sample_1)**2 + sem(sample_2)**2)\n", " sed = sqrt(sem(sample_1)**2 + sem(sample_2)**2)\n",
@ -119,7 +120,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 256, "execution_count": 160,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -128,36 +129,34 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def t_stat_dep(sample_1, sample_2):\n", "def t_stat_dep(sample_1, sample_2, mu=0):\n",
" \"\"\"Funkcja oblicza wartość statystyki testowej dla dwóch próbek zależnych\"\"\"\n", " \"\"\"Funkcja oblicza wartość statystyki testowej dla dwóch próbek zależnych\"\"\"\n",
" # TODO: Wywalić min\n", " if sample_1.empty or sample_2.empty:\n",
" # TODO: Przenieść mu jako opcjonalny argument?\n", " raise Exception(\"Empty sample\")\n",
" sample_1 = sample_1[0].values.tolist()\n", " sample_1 = sample_1[0].values.tolist()\n",
" sample_2 = sample_2[0].values.tolist()\n", " sample_2 = sample_2[0].values.tolist()\n",
" differences = [x_1 - x_2 for x_1, x_2 in zip(sample_1, sample_2)]\n", " differences = [x_1 - x_2 for x_1, x_2 in zip(sample_1, sample_2)]\n",
" sample_size = len(sample_1)\n", " sample_size = len(sample_1)\n",
" mu = 0 # The constant is zero if we want to test whether the average of the difference is significantly different.\n", " return (mean(differences) - mu) / (stdev(differences) / sqrt(sample_size))"
" return (mean(differences) - mu) / (stdev(differences) / min(0.00000001, sqrt(sample_size)))"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 257, "execution_count": 161,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def df_dep(sample_1, sample_2):\n", "def df_dep(sample_1, sample_2):\n",
" \"\"\"Funkcja oblicza stopnie swobody dla dwóch próbek zależnych\"\"\"\n", " \"\"\"Funkcja oblicza stopnie swobody dla dwóch próbek zależnych\"\"\"\n",
" # TODO: Assert działa chyba tylko w trybie debugowania\n",
" l1, l2 = len(sample_1), len(sample_2)\n", " l1, l2 = len(sample_1), len(sample_2)\n",
" assert l1 == l2 \n", " if l1 != l2:\n",
"\n", " raise Exception(\"Samples aren't of equal length\")\n",
" return l1" " return l1"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 258, "execution_count": 162,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -168,7 +167,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 259, "execution_count": 163,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -180,7 +179,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 260, "execution_count": 164,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -191,7 +190,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 261, "execution_count": 165,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
@ -202,7 +201,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 262, "execution_count": 166,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -211,17 +210,18 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def bootstrap_one_sample(sample):\n", "def bootstrap_one_sample(sample, population_mean):\n",
" return t_test(\n", " return t_test(\n",
" sample_1=sample,\n", " sample_1=sample,\n",
" df_fn=df_single,\n", " df_fn=df_single,\n",
" t_stat_fn=t_stat_single\n", " t_stat_fn=t_stat_single,\n",
" population_mean=population_mean\n",
" )" " )"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 263, "execution_count": 167,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -241,7 +241,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 264, "execution_count": 168,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -261,31 +261,33 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 265, "execution_count": 169,
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [ "source": [
"def get_t_stats(sample_1, sample_2=None, t_stat_fn=t_stat_ind):\n", "def get_t_stats(sample_1, sample_2=None, t_stat_fn=t_stat_single, population_mean=None):\n",
" \"\"\"Funkcja oblicza listę statystyk testowych dla każdej próbki bootstrapowej wybranej na podstawie danych sample_1 i sample_2\"\"\"\n", " \"\"\"Funkcja oblicza listę statystyk testowych dla każdej próbki bootstrapowej wybranej na podstawie danych sample_1 i sample_2\"\"\"\n",
" t_stat_list = []\n", " t_stat_list = []\n",
"\n", "\n",
" # Separate case for single tests\n", " # One sample test\n",
" if sample_2 is None:\n", " if t_stat_fn==t_stat_single:\n",
" if not population_mean:\n",
" raise Exception(\"population_mean not provided\")\n",
" for bootstrap in generate_bootstraps(sample_1):\n", " for bootstrap in generate_bootstraps(sample_1):\n",
" stat = t_stat_fn(bootstrap)\n", " stat = t_stat_fn(bootstrap, population_mean)\n",
" t_stat_list.append(stat)\n", " t_stat_list.append(stat)\n",
" return t_stat_list\n", " return t_stat_list\n",
"\n", "\n",
" # Two sample test\n",
" for bootstrap_1, bootstrap_2 in zip(generate_bootstraps(sample_1), generate_bootstraps(sample_2)):\n", " for bootstrap_1, bootstrap_2 in zip(generate_bootstraps(sample_1), generate_bootstraps(sample_2)):\n",
" stat = t_stat_fn(bootstrap_1, bootstrap_2)\n", " stat = t_stat_fn(bootstrap_1, bootstrap_2)\n",
" t_stat_list.append(stat)\n", " t_stat_list.append(stat)\n",
" \n",
" return t_stat_list" " return t_stat_list"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 266, "execution_count": 170,
"metadata": { "metadata": {
"pycharm": { "pycharm": {
"name": "#%%\n" "name": "#%%\n"
@ -293,34 +295,34 @@
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"def t_test(sample_1, sample_2=None, df_fn=df_ind, t_stat_fn=t_stat_ind, alpha=0.05):\n", "def t_test(sample_1, sample_2=None, df_fn=df_single, t_stat_fn=t_stat_single, population_mean=None, alpha=0.05):\n",
" \"\"\"\n", " \"\"\"\n",
" Funkcja przeprowadza test T-studenta dla dwóch zmiennych.\n", " Funkcja przeprowadza test T-studenta dla dwóch zmiennych.\n",
" liczba kolumn wynosi 1, test jest przeprowadzany dla jednej zmiennej.\n", " liczba kolumn wynosi 1, test jest przeprowadzany dla jednej zmiennej.\n",
" @param df_fn - funkcja obliczająca stopnie swobody\n", " @param df_fn - funkcja obliczająca stopnie swobody\n",
" @param t_stat_fn - funkcja obliczająca statystykę T\n", " @param t_stat_fn - funkcja obliczająca statystykę T\n",
" \"\"\"\n", " \"\"\"\n",
" t_stat_list = get_t_stats(sample_1, sample_2, t_stat_fn)\n", " t_stat_list = get_t_stats(sample_1, sample_2, t_stat_fn, population_mean=population_mean)\n",
" t_stat_sum = sum(t_stat_list)\n", " t_stat_sum = sum(t_stat_list)\n",
"\n", "\n",
" data_size = sample_1.shape[0]\n", " data_size = sample_1.shape[0]\n",
"\n", "\n",
" t_stat = t_stat_sum / data_size\n", " t_stat = t_stat_sum / data_size\n",
" # TODO: dolna i górna opcja dają inne wyniki z jakiegoś powodu (???)\n",
" t_stat = mean(t_stat_list)\n",
"\n", "\n",
" df = 0.0\n",
" if sample_2 is None:\n", " if sample_2 is None:\n",
" df = df_fn(sample_1)\n", " df = df_fn(sample_1)\n",
" else:\n", " else:\n",
" df = df_fn(sample_1, sample_2)\n", " df = df_fn(sample_1, sample_2)\n",
" cv = calculate_cv(df, alpha)\n", " cv = calculate_cv(df, alpha)\n",
" p = calculate_p(t_stat, df)\n", " p = calculate_p(t_stat, df)\n",
" \n",
" return t_stat, df, cv, p, t_stat_list" " return t_stat, df, cv, p, t_stat_list"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 267, "execution_count": 171,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -332,7 +334,7 @@
"def draw_distribution(stats):\n", "def draw_distribution(stats):\n",
" \"\"\"\n", " \"\"\"\n",
" Funkcja rysuje rozkład statystyki testowej\n", " Funkcja rysuje rozkład statystyki testowej\n",
" stats: lista statystyk testowych\n", " @param stats: lista statystyk testowych\n",
" \"\"\"\n", " \"\"\"\n",
" plt.hist(stats)\n", " plt.hist(stats)\n",
" plt.xlabel('Test statistic value')\n", " plt.xlabel('Test statistic value')\n",
@ -342,23 +344,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 268, "execution_count": 172,
"metadata": {
"collapsed": false,
"pycharm": {
"name": "#%%\n"
}
},
"outputs": [],
"source": [
"def make_decision(data, columns):\n",
" # TODO: Potrzebna ta funkcja w ogóle? Decyzja jest zależna od wybranych hipotez chyba.\n",
" pass"
]
},
{
"cell_type": "code",
"execution_count": 269,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -371,7 +357,7 @@
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Statystyka testowa dla jednej próby:\n", "Statystyka testowa dla jednej próby:\n",
"6.324555320336758e-09 - z naszej funkcji\n", "1.414213562373095 - z naszej funkcji\n",
"[1.41421356] - z gotowej biblioteki\n", "[1.41421356] - z gotowej biblioteki\n",
"\n", "\n",
"Statystyka testowa dla dwóch prób niezależnych:\n", "Statystyka testowa dla dwóch prób niezależnych:\n",
@ -379,7 +365,7 @@
"[-3.] - z gotowej biblioteki\n", "[-3.] - z gotowej biblioteki\n",
"\n", "\n",
"Statystyka testowa dla dwóch prób zależnych:\n", "Statystyka testowa dla dwóch prób zależnych:\n",
"-7.302967433402215e-09 - z naszej funkcji\n", "-1.6329931618554525 - z naszej funkcji\n",
"[-1.63299316] - z gotowej biblioteki\n", "[-1.63299316] - z gotowej biblioteki\n",
"\n" "\n"
] ]
@ -412,28 +398,22 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 270, "execution_count": 173,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"Statystyki dla jednej próby:\n" "Statystyki dla jednej próby:\n",
] "t: 1.8524997668616348, df: 5, cv: 2.015048372669157, p: 0.12315232406912302\n",
}, "\n",
{ "Statystyki dla dwóch prób zależnych:\n",
"ename": "TypeError", "t: 3.166992562129946, df: 5, cv: 2.015048372669157, p: 0.02489883191814224\n",
"evalue": "t_stat_single() missing 1 required positional argument: 'population_mean'", "\n",
"output_type": "error", "Statystyki dla dwóch prób niezależnych:\n",
"traceback": [ "t: 3.0429202631473986, df: 8, cv: 1.8595480375228421, p: 0.015992147409949586\n",
"\u001B[1;31m---------------------------------------------------------------------------\u001B[0m", "\n"
"\u001B[1;31mTypeError\u001B[0m Traceback (most recent call last)",
"Input \u001B[1;32mIn [270]\u001B[0m, in \u001B[0;36m<cell line: 7>\u001B[1;34m()\u001B[0m\n\u001B[0;32m 4\u001B[0m \u001B[38;5;28mprint\u001B[39m(\u001B[38;5;124mf\u001B[39m\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mt: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mt_stat\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m, df: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mdf\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m, cv: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mcv\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;124m, p: \u001B[39m\u001B[38;5;132;01m{\u001B[39;00mp\u001B[38;5;132;01m}\u001B[39;00m\u001B[38;5;130;01m\\n\u001B[39;00m\u001B[38;5;124m'\u001B[39m)\n\u001B[0;32m 6\u001B[0m \u001B[38;5;28mprint\u001B[39m(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mStatystyki dla jednej próby:\u001B[39m\u001B[38;5;124m'\u001B[39m)\n\u001B[1;32m----> 7\u001B[0m t_stat, df, cv, p, _ \u001B[38;5;241m=\u001B[39m \u001B[43mbootstrap_one_sample\u001B[49m\u001B[43m(\u001B[49m\u001B[43mdummy\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m 8\u001B[0m pretty_print_full_stats(t_stat, df, cv, p)\n\u001B[0;32m 10\u001B[0m \u001B[38;5;28mprint\u001B[39m(\u001B[38;5;124m'\u001B[39m\u001B[38;5;124mStatystyki dla dwóch prób zależnych:\u001B[39m\u001B[38;5;124m'\u001B[39m)\n",
"Input \u001B[1;32mIn [262]\u001B[0m, in \u001B[0;36mbootstrap_one_sample\u001B[1;34m(sample)\u001B[0m\n\u001B[0;32m 1\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mbootstrap_one_sample\u001B[39m(sample):\n\u001B[1;32m----> 2\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mt_test\u001B[49m\u001B[43m(\u001B[49m\n\u001B[0;32m 3\u001B[0m \u001B[43m \u001B[49m\u001B[43msample_1\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43msample\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m 4\u001B[0m \u001B[43m \u001B[49m\u001B[43mdf_fn\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mdf_single\u001B[49m\u001B[43m,\u001B[49m\n\u001B[0;32m 5\u001B[0m \u001B[43m \u001B[49m\u001B[43mt_stat_fn\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mt_stat_single\u001B[49m\n\u001B[0;32m 6\u001B[0m \u001B[43m \u001B[49m\u001B[43m)\u001B[49m\n",
"Input \u001B[1;32mIn [266]\u001B[0m, in \u001B[0;36mt_test\u001B[1;34m(sample_1, sample_2, df_fn, t_stat_fn, alpha)\u001B[0m\n\u001B[0;32m 1\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mt_test\u001B[39m(sample_1, sample_2\u001B[38;5;241m=\u001B[39m\u001B[38;5;28;01mNone\u001B[39;00m, df_fn\u001B[38;5;241m=\u001B[39mdf_ind, t_stat_fn\u001B[38;5;241m=\u001B[39mt_stat_ind, alpha\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m0.05\u001B[39m):\n\u001B[0;32m 2\u001B[0m \u001B[38;5;124;03m\"\"\"\u001B[39;00m\n\u001B[0;32m 3\u001B[0m \u001B[38;5;124;03m Funkcja przeprowadza test T-studenta dla dwóch zmiennych.\u001B[39;00m\n\u001B[0;32m 4\u001B[0m \u001B[38;5;124;03m liczba kolumn wynosi 1, test jest przeprowadzany dla jednej zmiennej.\u001B[39;00m\n\u001B[0;32m 5\u001B[0m \u001B[38;5;124;03m @param df_fn - funkcja obliczająca stopnie swobody\u001B[39;00m\n\u001B[0;32m 6\u001B[0m \u001B[38;5;124;03m @param t_stat_fn - funkcja obliczająca statystykę T\u001B[39;00m\n\u001B[0;32m 7\u001B[0m \u001B[38;5;124;03m \"\"\"\u001B[39;00m\n\u001B[1;32m----> 8\u001B[0m t_stat_list \u001B[38;5;241m=\u001B[39m \u001B[43mget_t_stats\u001B[49m\u001B[43m(\u001B[49m\u001B[43msample_1\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43msample_2\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mt_stat_fn\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m 9\u001B[0m t_stat_sum \u001B[38;5;241m=\u001B[39m \u001B[38;5;28msum\u001B[39m(t_stat_list)\n\u001B[0;32m 11\u001B[0m data_size \u001B[38;5;241m=\u001B[39m sample_1\u001B[38;5;241m.\u001B[39mshape[\u001B[38;5;241m0\u001B[39m]\n",
"Input \u001B[1;32mIn [265]\u001B[0m, in \u001B[0;36mget_t_stats\u001B[1;34m(sample_1, sample_2, t_stat_fn)\u001B[0m\n\u001B[0;32m 6\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m sample_2 \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m 7\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m bootstrap \u001B[38;5;129;01min\u001B[39;00m generate_bootstraps(sample_1):\n\u001B[1;32m----> 8\u001B[0m stat \u001B[38;5;241m=\u001B[39m \u001B[43mt_stat_fn\u001B[49m\u001B[43m(\u001B[49m\u001B[43mbootstrap\u001B[49m\u001B[43m)\u001B[49m\n\u001B[0;32m 9\u001B[0m t_stat_list\u001B[38;5;241m.\u001B[39mappend(stat)\n\u001B[0;32m 10\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m t_stat_list\n",
"\u001B[1;31mTypeError\u001B[0m: t_stat_single() missing 1 required positional argument: 'population_mean'"
] ]
} }
], ],
@ -444,7 +424,7 @@
" print(f't: {t_stat}, df: {df}, cv: {cv}, p: {p}\\n')\n", " print(f't: {t_stat}, df: {df}, cv: {cv}, p: {p}\\n')\n",
"\n", "\n",
"print('Statystyki dla jednej próby:')\n", "print('Statystyki dla jednej próby:')\n",
"t_stat, df, cv, p, _ = bootstrap_one_sample(dummy)\n", "t_stat, df, cv, p, _ = bootstrap_one_sample(dummy, 2)\n",
"pretty_print_full_stats(t_stat, df, cv, p)\n", "pretty_print_full_stats(t_stat, df, cv, p)\n",
"\n", "\n",
"print('Statystyki dla dwóch prób zależnych:')\n", "print('Statystyki dla dwóch prób zależnych:')\n",
@ -458,7 +438,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 174,
"metadata": { "metadata": {
"collapsed": false, "collapsed": false,
"pycharm": { "pycharm": {
@ -468,7 +448,7 @@
"outputs": [], "outputs": [],
"source": [ "source": [
"dataset = pd.read_csv('experiment_data.csv')\n", "dataset = pd.read_csv('experiment_data.csv')\n",
"make_decision(dataset, ['Weight', 'Age'])" "#make_decision(dataset, ['Weight', 'Age'])"
] ]
} }
], ],