diff --git a/lab-hypothesis-testing.ipynb b/lab-hypothesis-testing.ipynb
index 0cc26d5..487676a 100644
--- a/lab-hypothesis-testing.ipynb
+++ b/lab-hypothesis-testing.ipynb
@@ -51,7 +51,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 18,
"metadata": {},
"outputs": [
{
@@ -278,7 +278,7 @@
"[800 rows x 11 columns]"
]
},
- "execution_count": 3,
+ "execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
@@ -297,11 +297,36 @@
},
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": null,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "np.float64(0.0007993609745420597)"
+ ]
+ },
+ "execution_count": 13,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
"source": [
- "#code here"
+ "\n",
+ "HP_Pokemons = df[df['Type 1'] == 'Dragon']['HP']\n",
+ "HP_Grass = df[df['Type 1'] == 'Grass']['HP']\n",
+ "\n",
+ "# H0: Average_HP_Pokemons = Average_HP_Grass\n",
+ "# H1: Average_HP_Pokemons > Average_HP_Grass\n",
+ "\n",
+ "# alpha = 0.05 \n",
+ "\n",
+ "# two sample t-test --> test the means of two independent samples of scores.\n",
+ "_,p_value = st.ttest_ind(HP_Pokemons,HP_Grass,alternative='greater',equal_var=False)\n",
+ "p_value\n",
+ "\n",
+ "# conclusion- -> reject H0, so type dragon have average more HP than type grass\n",
+ "\n"
]
},
{
@@ -313,11 +338,48 @@
},
{
"cell_type": "code",
- "execution_count": 18,
+ "execution_count": null,
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " Multivariate linear model\n",
+ "================================================================\n",
+ " \n",
+ "----------------------------------------------------------------\n",
+ " Intercept Value Num DF Den DF F Value Pr > F\n",
+ "----------------------------------------------------------------\n",
+ " Wilks' lambda 0.0592 6.0000 793.0000 2100.8338 0.0000\n",
+ " Pillai's trace 0.9408 6.0000 793.0000 2100.8338 0.0000\n",
+ " Hotelling-Lawley trace 15.8953 6.0000 793.0000 2100.8338 0.0000\n",
+ " Roy's greatest root 15.8953 6.0000 793.0000 2100.8338 0.0000\n",
+ "----------------------------------------------------------------\n",
+ " \n",
+ "----------------------------------------------------------------\n",
+ " Legendary Value Num DF Den DF F Value Pr > F\n",
+ "----------------------------------------------------------------\n",
+ " Wilks' lambda 0.7331 6.0000 793.0000 48.1098 0.0000\n",
+ " Pillai's trace 0.2669 6.0000 793.0000 48.1098 0.0000\n",
+ " Hotelling-Lawley trace 0.3640 6.0000 793.0000 48.1098 0.0000\n",
+ " Roy's greatest root 0.3640 6.0000 793.0000 48.1098 0.0000\n",
+ "================================================================\n",
+ "\n"
+ ]
+ }
+ ],
"source": [
- "#code here"
+ "\n",
+ "from statsmodels.multivariate.manova import MANOVA\n",
+ "from patsy import dmatrix\n",
+ "\n",
+ "# H0: Legendary and Non-Legendary Pokémon have the same multivariate mean vector of stats (HP, Attack, Defense, Sp.Atk, Sp.Def, Speed).\n",
+ "# H1: At least one of the stats’ mean differs, i.e., the multivariate mean vectors are not equal between Legendary and Non-Legendary Pokémon. \n",
+ "maov = MANOVA.from_formula('HP + Attack + Defense + Q(\"Sp. Atk\") + Q(\"Sp. Def\") + Speed ~ Legendary', data=df)\n",
+ "print(maov.mv_test())\n",
+ "\n",
+ "# by looking at Pr > F 0.0000, reject H0, so There is a statistically significant difference in the combined stats (HP, Attack, Defense, Sp.Atk, Sp.Def, Speed) between Legendary and Non-Legendary Pokémon."
]
},
{
@@ -337,7 +399,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 47,
"metadata": {},
"outputs": [
{
@@ -433,34 +495,121 @@
" | 1.9250 | \n",
" 65500.0 | \n",
" \n",
+ " \n",
+ " | ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ " ... | \n",
+ "
\n",
+ " \n",
+ " | 16995 | \n",
+ " -124.26 | \n",
+ " 40.58 | \n",
+ " 52.0 | \n",
+ " 2217.0 | \n",
+ " 394.0 | \n",
+ " 907.0 | \n",
+ " 369.0 | \n",
+ " 2.3571 | \n",
+ " 111400.0 | \n",
+ "
\n",
+ " \n",
+ " | 16996 | \n",
+ " -124.27 | \n",
+ " 40.69 | \n",
+ " 36.0 | \n",
+ " 2349.0 | \n",
+ " 528.0 | \n",
+ " 1194.0 | \n",
+ " 465.0 | \n",
+ " 2.5179 | \n",
+ " 79000.0 | \n",
+ "
\n",
+ " \n",
+ " | 16997 | \n",
+ " -124.30 | \n",
+ " 41.84 | \n",
+ " 17.0 | \n",
+ " 2677.0 | \n",
+ " 531.0 | \n",
+ " 1244.0 | \n",
+ " 456.0 | \n",
+ " 3.0313 | \n",
+ " 103600.0 | \n",
+ "
\n",
+ " \n",
+ " | 16998 | \n",
+ " -124.30 | \n",
+ " 41.80 | \n",
+ " 19.0 | \n",
+ " 2672.0 | \n",
+ " 552.0 | \n",
+ " 1298.0 | \n",
+ " 478.0 | \n",
+ " 1.9797 | \n",
+ " 85800.0 | \n",
+ "
\n",
+ " \n",
+ " | 16999 | \n",
+ " -124.35 | \n",
+ " 40.54 | \n",
+ " 52.0 | \n",
+ " 1820.0 | \n",
+ " 300.0 | \n",
+ " 806.0 | \n",
+ " 270.0 | \n",
+ " 3.0147 | \n",
+ " 94600.0 | \n",
+ "
\n",
" \n",
"\n",
+ "17000 rows × 9 columns
\n",
""
],
"text/plain": [
- " longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
- "0 -114.31 34.19 15.0 5612.0 1283.0 \n",
- "1 -114.47 34.40 19.0 7650.0 1901.0 \n",
- "2 -114.56 33.69 17.0 720.0 174.0 \n",
- "3 -114.57 33.64 14.0 1501.0 337.0 \n",
- "4 -114.57 33.57 20.0 1454.0 326.0 \n",
+ " longitude latitude housing_median_age total_rooms total_bedrooms \\\n",
+ "0 -114.31 34.19 15.0 5612.0 1283.0 \n",
+ "1 -114.47 34.40 19.0 7650.0 1901.0 \n",
+ "2 -114.56 33.69 17.0 720.0 174.0 \n",
+ "3 -114.57 33.64 14.0 1501.0 337.0 \n",
+ "4 -114.57 33.57 20.0 1454.0 326.0 \n",
+ "... ... ... ... ... ... \n",
+ "16995 -124.26 40.58 52.0 2217.0 394.0 \n",
+ "16996 -124.27 40.69 36.0 2349.0 528.0 \n",
+ "16997 -124.30 41.84 17.0 2677.0 531.0 \n",
+ "16998 -124.30 41.80 19.0 2672.0 552.0 \n",
+ "16999 -124.35 40.54 52.0 1820.0 300.0 \n",
"\n",
- " population households median_income median_house_value \n",
- "0 1015.0 472.0 1.4936 66900.0 \n",
- "1 1129.0 463.0 1.8200 80100.0 \n",
- "2 333.0 117.0 1.6509 85700.0 \n",
- "3 515.0 226.0 3.1917 73400.0 \n",
- "4 624.0 262.0 1.9250 65500.0 "
+ " population households median_income median_house_value \n",
+ "0 1015.0 472.0 1.4936 66900.0 \n",
+ "1 1129.0 463.0 1.8200 80100.0 \n",
+ "2 333.0 117.0 1.6509 85700.0 \n",
+ "3 515.0 226.0 3.1917 73400.0 \n",
+ "4 624.0 262.0 1.9250 65500.0 \n",
+ "... ... ... ... ... \n",
+ "16995 907.0 369.0 2.3571 111400.0 \n",
+ "16996 1194.0 465.0 2.5179 79000.0 \n",
+ "16997 1244.0 456.0 3.0313 103600.0 \n",
+ "16998 1298.0 478.0 1.9797 85800.0 \n",
+ "16999 806.0 270.0 3.0147 94600.0 \n",
+ "\n",
+ "[17000 rows x 9 columns]"
]
},
- "execution_count": 5,
+ "execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv(\"https://raw.githubusercontent.com/data-bootcamp-v4/data/main/california_housing.csv\")\n",
- "df.head()"
+ "df"
]
},
{
@@ -483,22 +632,93 @@
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 70,
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "import math\n",
+ "\n",
+ "school_location = (-118, 34)\n",
+ "hospital_location = (-122, 37)\n"
+ ]
},
{
"cell_type": "code",
- "execution_count": null,
+ "execution_count": 71,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Write a function to calculate euclidean distance from each house (neighborhood) to the school and to the hospital.\n",
+ "\n",
+ "def calculate_distance(row,location):\n",
+ " return math.sqrt((row['longitude'] - location[0])**2 + (row['latitude'] - location[1])**2)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "df['dis_from_school'] = df.apply(calculate_distance,args=(school_location, ),axis= 1)\n",
+ "df['dis_from_hospital'] = df.apply(calculate_distance,args=(hospital_location, ),axis= 1)\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# We consider a house (neighborhood) to be close to a school or hospital if the distance is lower than 0.50.\n",
+ "\n",
+ "df['close_or_far'] = df.apply(lambda row: 'close' if (row['dis_from_school'] < 0.5) or (row['dis_from_school'] < 0.5) else 'far',axis=1)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 77,
"metadata": {},
"outputs": [],
- "source": []
+ "source": [
+ "# - Divide your dataset into houses close and far from either a hospital or school.\n",
+ "\n",
+ "s_close = df[df['close_or_far'] == 'close']['median_house_value']\n",
+ "s_far = df[df['close_or_far'] == 'far']['median_house_value']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "F_onewayResult(statistic=np.float64(577.462645674138), pvalue=np.float64(1.6450819839186202e-125))"
+ ]
+ },
+ "execution_count": 86,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# HO: houses are priced same no matter they are close to or far from school or hospital\n",
+ "# H1: houses close to either a school or a hospital are more expensive\n",
+ "\n",
+ "\n",
+ "# anova test \n",
+ "st.f_oneway(s_close,s_far)\n",
+ "\n",
+ "# p-value = 1.6450819839186202e-125 < 0.05, so reject H0, so houses close to either a school or a hospital are more statistically more expensive "
+ ]
}
],
"metadata": {
"kernelspec": {
- "display_name": "Python 3",
+ "display_name": "py310",
"language": "python",
"name": "python3"
},
@@ -512,7 +732,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.10.9"
+ "version": "3.10.18"
}
},
"nbformat": 4,