Skip to content

[lab-hypothesis-testing-2] Henrik Söder #185

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
HenrikSoeder wants to merge 1 commit into
base: master
Choose a base branch
from
Open

[lab-hypothesis-testing-2] Henrik Söder #185

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
275 changes: 248 additions & 27 deletions your-code/challenge-1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,12 +19,13 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"# Import libraries\n",
"import pandas as pd"
"import pandas as pd\n",
"import numpy as np\n",
"import scipy.stats as st"
]
},
{
Expand All @@ -38,11 +39,138 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"execution_count": 6,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>#</th>\n",
" <th>Name</th>\n",
" <th>Type 1</th>\n",
" <th>Type 2</th>\n",
" <th>Total</th>\n",
" <th>HP</th>\n",
" <th>Attack</th>\n",
" <th>Defense</th>\n",
" <th>Sp. Atk</th>\n",
" <th>Sp. Def</th>\n",
" <th>Speed</th>\n",
" <th>Generation</th>\n",
" <th>Legendary</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>Bulbasaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>318</td>\n",
" <td>45</td>\n",
" <td>49</td>\n",
" <td>49</td>\n",
" <td>65</td>\n",
" <td>65</td>\n",
" <td>45</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>Ivysaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>405</td>\n",
" <td>60</td>\n",
" <td>62</td>\n",
" <td>63</td>\n",
" <td>80</td>\n",
" <td>80</td>\n",
" <td>60</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>Venusaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>525</td>\n",
" <td>80</td>\n",
" <td>82</td>\n",
" <td>83</td>\n",
" <td>100</td>\n",
" <td>100</td>\n",
" <td>80</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>VenusaurMega Venusaur</td>\n",
" <td>Grass</td>\n",
" <td>Poison</td>\n",
" <td>625</td>\n",
" <td>80</td>\n",
" <td>100</td>\n",
" <td>123</td>\n",
" <td>122</td>\n",
" <td>120</td>\n",
" <td>80</td>\n",
" <td>1</td>\n",
" <td>False</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" # Name Type 1 Type 2 Total HP Attack Defense \\\n",
"0 1 Bulbasaur Grass Poison 318 45 49 49 \n",
"1 2 Ivysaur Grass Poison 405 60 62 63 \n",
"2 3 Venusaur Grass Poison 525 80 82 83 \n",
"3 3 VenusaurMega Venusaur Grass Poison 625 80 100 123 \n",
"\n",
" Sp. Atk Sp. Def Speed Generation Legendary \n",
"0 65 65 45 1 False \n",
"1 80 80 60 1 False \n",
"2 100 100 80 1 False \n",
"3 122 120 80 1 False "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Your code here:\n"
"pokemon = pd.read_csv(\"Pokemon.csv\")\n",
"pokemon.head(4)"
]
},
{
Expand All @@ -58,11 +186,12 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"def t_test_features(s1, s2, features=['HP', 'Attack', 'Defense', 'Sp. Atk', 'Sp. Def', 'Speed', 'Total']):\n",
" \n",
" \"\"\"Test means of a feature set of two samples\n",
" \n",
" Args:\n",
Expand All @@ -75,7 +204,19 @@
" \"\"\"\n",
" results = {}\n",
"\n",
" # Your code here\n",
" for x in features:\n",
" \n",
" sample_1 = s1[x]\n",
" sample_2 = s2[x]\n",
"\n",
" # H0 = sample 1 mu = sample2 mu\n",
" # H1 = sample 1 mu != sample2 mu\n",
" output = st.ttest_ind(sample_1, sample_2, equal_var = False)\n",
" p_value = output[1]\n",
"\n",
"\n",
" results[x] = p_value\n",
"\n",
" \n",
" return results"
]
Expand All @@ -101,11 +242,31 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 39,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"{'HP': 1.0026911708035284e-13,\n",
" 'Attack': 2.5203724492366553e-16,\n",
" 'Defense': 4.8269984949193316e-11,\n",
" 'Sp. Atk': 1.5514614112239705e-21,\n",
" 'Sp. Def': 2.294932786405291e-15,\n",
" 'Speed': 1.0490163118824585e-18,\n",
" 'Total': 9.357954335957446e-47}"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Your code here\n"
"df1 = pokemon[pokemon[\"Legendary\"] == True]\n",
"df2 = pokemon[pokemon[\"Legendary\"] == False]\n",
"\n",
"t_test_features(df1, df2)"
]
},
{
Expand All @@ -121,7 +282,8 @@
"metadata": {},
"outputs": [],
"source": [
"# Your comment here"
"# since the hypothesis was that they have the same mean values, and the hypothesis was rejected,\n",
"# the conclusion can be made that they have different values"
]
},
{
Expand All @@ -133,11 +295,31 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 41,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"{'HP': 0.14551697834219632,\n",
" 'Attack': 0.24721958967217725,\n",
" 'Defense': 0.5677711011725426,\n",
" 'Sp. Atk': 0.12332165977104392,\n",
" 'Sp. Def': 0.18829872292645758,\n",
" 'Speed': 0.0023926593731213508,\n",
" 'Total': 0.5631377907941676}"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Your code here\n"
"df1 = pokemon[pokemon[\"Generation\"] == 1]\n",
"df2 = pokemon[pokemon[\"Generation\"] == 2]\n",
"\n",
"t_test_features(df1, df2)\n"
]
},
{
Expand All @@ -153,7 +335,8 @@
"metadata": {},
"outputs": [],
"source": [
"# Your comment here"
"# the conclusion can be made, that we can NOT reject the hypothesis that they differ from each other\n",
"# therefore they might have similiar values, but we DONT KNOW"
]
},
{
Expand All @@ -165,11 +348,34 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 56,
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"{'HP': 0.11314389855379418,\n",
" 'Attack': 0.00014932578145948305,\n",
" 'Defense': 2.797854041151469e-08,\n",
" 'Sp. Atk': 0.00013876216585667901,\n",
" 'Sp. Def': 0.00010730610934512777,\n",
" 'Speed': 0.024217032818190928,\n",
" 'Total': 1.1157056505229961e-07}"
]
},
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Your code here\n"
"one_type = pokemon[pokemon[\"Type 2\"].isnull() == True]\n",
"two_type = pokemon[pokemon[\"Type 2\"].isnull() == False]\n",
"\n",
"df1 = one_type\n",
"df2 = two_type\n",
"\n",
"t_test_features(df1, df2)"
]
},
{
Expand All @@ -185,7 +391,8 @@
"metadata": {},
"outputs": [],
"source": [
"# Your comment here"
"# we can obtain from the \"total\" column (where the hypothesis got rejected),\n",
"# that they indeed have different values"
]
},
{
Expand All @@ -199,11 +406,24 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 61,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"p_value for attack and defense: 0.0012123980547317907\n",
"p_value for Sp. attack and Sp. defense: 0.5458436328840434\n"
]
}
],
"source": [
"# Your code here\n"
"attack_defense = st.f_oneway(pokemon[\"Attack\"], pokemon[\"Defense\"])\n",
"print(\"p_value for attack and defense: \",attack_defense[1])\n",
"\n",
"spatt_spdef = st.f_oneway(pokemon[\"Sp. Atk\"], pokemon[\"Sp. Def\"])\n",
"print(\"p_value for Sp. attack and Sp. defense: \",spatt_spdef[1])"
]
},
{
Expand All @@ -219,13 +439,14 @@
"metadata": {},
"outputs": [],
"source": [
"# Your comment here"
"# there are significant differences between \"Attack\" and \"Defense\"\n",
"# we can not say if there are differences between \"Sp. Attack\" and \"Sp. defense\""
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -239,7 +460,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.3"
"version": "3.11.4"
}
},
"nbformat": 4,
Expand Down
Loading