Skip to content

Solved lab #526

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
claireley wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Solved lab #526

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
136 changes: 112 additions & 24 deletions lab-hypothesis-testing.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -51,7 +51,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 46,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -278,7 +278,7 @@
"[800 rows x 11 columns]"
]
},
"execution_count": 3,
"execution_count": 46,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -297,11 +297,26 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 53,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n"
]
}
],
"source": [
"#code here"
"#code here\n",
"df_dragon = df[df[\"Type 1\"]==\"Dragon\"][\"HP\"]\n",
"df_grass = df[df[\"Type 1\"]==\"Grass\"][\"HP\"]\n",
"t_stat, p_value = st.ttest_ind(df_dragon,df_grass, equal_var=False, alternative=\"greater\")\n",
"print(p_value < 0.05)\n",
"\n",
"#p-value is less than alpha (0.05), \n",
"#reject the null hypothesis that HP stats are the same, accept alternative that Dragon have greater average HP stats"
]
},
{
Expand All @@ -313,11 +328,63 @@
},
{
"cell_type": "code",
"execution_count": 18,
"execution_count": 55,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"HP\n",
"True\n",
"Attack\n",
"True\n",
"Defense\n",
"True\n",
"Sp. Atk\n",
"True\n",
"Sp. Def\n",
"True\n",
"Speed\n",
"True\n"
]
},
{
"data": {
"text/plain": [
"{'HP': (np.float64(8.981370483625046), np.float64(1.0026911708035284e-13)),\n",
" 'Attack': (np.float64(10.438133539322203), np.float64(2.520372449236646e-16)),\n",
" 'Defense': (np.float64(7.637078164784618),\n",
" np.float64(4.8269984949193316e-11)),\n",
" 'Sp. Atk': (np.float64(13.417449984138461),\n",
" np.float64(1.5514614112239812e-21)),\n",
" 'Sp. Def': (np.float64(10.015696613114878),\n",
" np.float64(2.2949327864052826e-15)),\n",
" 'Speed': (np.float64(11.47504444631443), np.float64(1.049016311882451e-18))}"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#code here"
"from scipy.stats import ttest_ind\n",
"\n",
"df_legendary = df[df[\"Legendary\"] == 1][['HP','Attack','Defense', 'Sp. Atk', 'Sp. Def', 'Speed']]\n",
"df_nonlegendary = df[df[\"Legendary\"] == 0][['HP','Attack','Defense', 'Sp. Atk', 'Sp. Def', 'Speed']]\n",
"\n",
"results = {}\n",
"\n",
"for col in df_legendary.columns:\n",
" t_stat, p_value = ttest_ind(df_legendary[col], df_nonlegendary[col], equal_var=False, alternative = 'two-sided')\n",
" results[col] = (t_stat, p_value)\n",
" print(col)\n",
" print(p_value<0.05)\n",
"results\n",
"\n",
"#p-values are all less than alpha (0.05), reject the null hypothesis that stats are the same, \n",
"# accept alternative that nonlegendary Pokemon have different stats"
]
},
{
Expand All @@ -337,7 +404,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 56,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -453,7 +520,7 @@
"4 624.0 262.0 1.9250 65500.0 "
]
},
"execution_count": 5,
"execution_count": 56,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -483,22 +550,43 @@
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 75,
"metadata": {},
"outputs": [],
"source": []
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n"
]
}
],
"source": [
"from scipy import stats\n",
"\n",
"school_x=-118\n",
"school_y=34\n",
"hospital_x=-122\n",
"hospital_y=37\n",
"\n",
"df['dist_school'] = np.sqrt((df['longitude']-school_x)**2 + (df['latitude']-school_y)**2)\n",
"df['dist_hospital'] = np.sqrt((df['longitude']-hospital_x)**2 + (df['latitude']-hospital_y)**2)\n",
"\n",
"s_h_close=df[(df.dist_school<0.5) | (df.dist_hospital<0.5) ]\n",
"s_h_far=df[(df.dist_school>=0.5) & (df.dist_hospital>=0.5) ]\n",
"\n",
"# # Two-sample t-test\n",
"t_stat, p_value = stats.ttest_ind(s_h_close['median_house_value'], s_h_far['median_house_value'], alternative='greater')\n",
"print(p_value < 0.05)\n",
"\n",
"#p-value is less than alpha (0.05), reject the null hypothesis median house values are the same, \n",
"#accept alternative that houses closer to schools or hospitals (Euclidean distance lower than 0.5) have a higher median value"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
Expand All @@ -512,9 +600,9 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.13.9"
}
},
"nbformat": 4,
"nbformat_minor": 2
"nbformat_minor": 4
}