{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#ipython"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# pandas: load data"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"DATA_PATH = '/usr/lib/python3/dist-packages/pandas/tests/data/tips.csv'"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"#!cat /usr/lib/python3/dist-packages/pandas/tests/data/tips.csv"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"data = pd.read_csv(DATA_PATH)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 5 \n",
" 25.29 \n",
" 4.71 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 6 \n",
" 8.77 \n",
" 2.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 7 \n",
" 26.88 \n",
" 3.12 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 8 \n",
" 15.04 \n",
" 1.96 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 9 \n",
" 14.78 \n",
" 3.23 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 10 \n",
" 10.27 \n",
" 1.71 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 11 \n",
" 35.26 \n",
" 5.00 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 12 \n",
" 15.42 \n",
" 1.57 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 13 \n",
" 18.43 \n",
" 3.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 14 \n",
" 14.83 \n",
" 3.02 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 15 \n",
" 21.58 \n",
" 3.92 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 16 \n",
" 10.33 \n",
" 1.67 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 17 \n",
" 16.29 \n",
" 3.71 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 18 \n",
" 16.97 \n",
" 3.50 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 19 \n",
" 20.65 \n",
" 3.35 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 20 \n",
" 17.92 \n",
" 4.08 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 21 \n",
" 20.29 \n",
" 2.75 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 22 \n",
" 15.77 \n",
" 2.23 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 23 \n",
" 39.42 \n",
" 7.58 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 24 \n",
" 19.82 \n",
" 3.18 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 25 \n",
" 17.81 \n",
" 2.34 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 26 \n",
" 13.37 \n",
" 2.00 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 27 \n",
" 12.69 \n",
" 2.00 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 28 \n",
" 21.70 \n",
" 4.30 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 29 \n",
" 19.65 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" \n",
" \n",
" 214 \n",
" 28.17 \n",
" 6.50 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 215 \n",
" 12.90 \n",
" 1.10 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 216 \n",
" 28.15 \n",
" 3.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 5 \n",
" \n",
" \n",
" 217 \n",
" 11.59 \n",
" 1.50 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 218 \n",
" 7.74 \n",
" 1.44 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 219 \n",
" 30.14 \n",
" 3.09 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 220 \n",
" 12.16 \n",
" 2.20 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 221 \n",
" 13.42 \n",
" 3.48 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 222 \n",
" 8.58 \n",
" 1.92 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 1 \n",
" \n",
" \n",
" 223 \n",
" 15.98 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Fri \n",
" Lunch \n",
" 3 \n",
" \n",
" \n",
" 224 \n",
" 13.42 \n",
" 1.58 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 225 \n",
" 16.27 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 226 \n",
" 10.09 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 227 \n",
" 20.45 \n",
" 3.00 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 228 \n",
" 13.28 \n",
" 2.72 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 229 \n",
" 22.12 \n",
" 2.88 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 230 \n",
" 24.01 \n",
" 2.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 231 \n",
" 15.69 \n",
" 3.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 232 \n",
" 11.61 \n",
" 3.39 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 233 \n",
" 10.77 \n",
" 1.47 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 234 \n",
" 15.53 \n",
" 3.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 235 \n",
" 10.07 \n",
" 1.25 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 236 \n",
" 12.60 \n",
" 1.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 237 \n",
" 32.83 \n",
" 1.17 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 238 \n",
" 35.83 \n",
" 4.67 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 239 \n",
" 29.03 \n",
" 5.92 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 240 \n",
" 27.18 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 241 \n",
" 22.67 \n",
" 2.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 242 \n",
" 17.82 \n",
" 1.75 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 243 \n",
" 18.78 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Thur \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
"
\n",
"
244 rows × 7 columns
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size\n",
"0 16.99 1.01 Female No Sun Dinner 2\n",
"1 10.34 1.66 Male No Sun Dinner 3\n",
"2 21.01 3.50 Male No Sun Dinner 3\n",
"3 23.68 3.31 Male No Sun Dinner 2\n",
"4 24.59 3.61 Female No Sun Dinner 4\n",
"5 25.29 4.71 Male No Sun Dinner 4\n",
"6 8.77 2.00 Male No Sun Dinner 2\n",
"7 26.88 3.12 Male No Sun Dinner 4\n",
"8 15.04 1.96 Male No Sun Dinner 2\n",
"9 14.78 3.23 Male No Sun Dinner 2\n",
"10 10.27 1.71 Male No Sun Dinner 2\n",
"11 35.26 5.00 Female No Sun Dinner 4\n",
"12 15.42 1.57 Male No Sun Dinner 2\n",
"13 18.43 3.00 Male No Sun Dinner 4\n",
"14 14.83 3.02 Female No Sun Dinner 2\n",
"15 21.58 3.92 Male No Sun Dinner 2\n",
"16 10.33 1.67 Female No Sun Dinner 3\n",
"17 16.29 3.71 Male No Sun Dinner 3\n",
"18 16.97 3.50 Female No Sun Dinner 3\n",
"19 20.65 3.35 Male No Sat Dinner 3\n",
"20 17.92 4.08 Male No Sat Dinner 2\n",
"21 20.29 2.75 Female No Sat Dinner 2\n",
"22 15.77 2.23 Female No Sat Dinner 2\n",
"23 39.42 7.58 Male No Sat Dinner 4\n",
"24 19.82 3.18 Male No Sat Dinner 2\n",
"25 17.81 2.34 Male No Sat Dinner 4\n",
"26 13.37 2.00 Male No Sat Dinner 2\n",
"27 12.69 2.00 Male No Sat Dinner 2\n",
"28 21.70 4.30 Male No Sat Dinner 2\n",
"29 19.65 3.00 Female No Sat Dinner 2\n",
".. ... ... ... ... ... ... ...\n",
"214 28.17 6.50 Female Yes Sat Dinner 3\n",
"215 12.90 1.10 Female Yes Sat Dinner 2\n",
"216 28.15 3.00 Male Yes Sat Dinner 5\n",
"217 11.59 1.50 Male Yes Sat Dinner 2\n",
"218 7.74 1.44 Male Yes Sat Dinner 2\n",
"219 30.14 3.09 Female Yes Sat Dinner 4\n",
"220 12.16 2.20 Male Yes Fri Lunch 2\n",
"221 13.42 3.48 Female Yes Fri Lunch 2\n",
"222 8.58 1.92 Male Yes Fri Lunch 1\n",
"223 15.98 3.00 Female No Fri Lunch 3\n",
"224 13.42 1.58 Male Yes Fri Lunch 2\n",
"225 16.27 2.50 Female Yes Fri Lunch 2\n",
"226 10.09 2.00 Female Yes Fri Lunch 2\n",
"227 20.45 3.00 Male No Sat Dinner 4\n",
"228 13.28 2.72 Male No Sat Dinner 2\n",
"229 22.12 2.88 Female Yes Sat Dinner 2\n",
"230 24.01 2.00 Male Yes Sat Dinner 4\n",
"231 15.69 3.00 Male Yes Sat Dinner 3\n",
"232 11.61 3.39 Male No Sat Dinner 2\n",
"233 10.77 1.47 Male No Sat Dinner 2\n",
"234 15.53 3.00 Male Yes Sat Dinner 2\n",
"235 10.07 1.25 Male No Sat Dinner 2\n",
"236 12.60 1.00 Male Yes Sat Dinner 2\n",
"237 32.83 1.17 Male Yes Sat Dinner 2\n",
"238 35.83 4.67 Female No Sat Dinner 3\n",
"239 29.03 5.92 Male No Sat Dinner 3\n",
"240 27.18 2.00 Female Yes Sat Dinner 2\n",
"241 22.67 2.00 Male Yes Sat Dinner 2\n",
"242 17.82 1.75 Male No Sat Dinner 2\n",
"243 18.78 3.00 Female No Thur Dinner 2\n",
"\n",
"[244 rows x 7 columns]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" \n",
" \n",
" \n",
" \n",
" 67 \n",
" 3.07 \n",
" 1.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 1 \n",
" \n",
" \n",
" 236 \n",
" 12.60 \n",
" 1.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 92 \n",
" 5.75 \n",
" 1.00 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 111 \n",
" 7.25 \n",
" 1.00 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 1 \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 215 \n",
" 12.90 \n",
" 1.10 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 237 \n",
" 32.83 \n",
" 1.17 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 235 \n",
" 10.07 \n",
" 1.25 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 75 \n",
" 10.51 \n",
" 1.25 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 135 \n",
" 8.51 \n",
" 1.25 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 43 \n",
" 9.68 \n",
" 1.32 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 146 \n",
" 18.64 \n",
" 1.36 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 3 \n",
" \n",
" \n",
" 218 \n",
" 7.74 \n",
" 1.44 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 195 \n",
" 7.56 \n",
" 1.44 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 30 \n",
" 9.55 \n",
" 1.45 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 233 \n",
" 10.77 \n",
" 1.47 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 126 \n",
" 8.52 \n",
" 1.48 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 190 \n",
" 15.69 \n",
" 1.50 \n",
" Male \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 57 \n",
" 26.41 \n",
" 1.50 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 97 \n",
" 12.03 \n",
" 1.50 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 99 \n",
" 12.46 \n",
" 1.50 \n",
" Male \n",
" No \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 117 \n",
" 10.65 \n",
" 1.50 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 132 \n",
" 11.17 \n",
" 1.50 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 217 \n",
" 11.59 \n",
" 1.50 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 145 \n",
" 8.35 \n",
" 1.50 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 130 \n",
" 19.08 \n",
" 1.50 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 53 \n",
" 9.94 \n",
" 1.56 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 12 \n",
" 15.42 \n",
" 1.57 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 224 \n",
" 13.42 \n",
" 1.58 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 168 \n",
" 10.59 \n",
" 1.61 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" \n",
" \n",
" 5 \n",
" 25.29 \n",
" 4.71 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 95 \n",
" 40.17 \n",
" 4.73 \n",
" Male \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 46 \n",
" 22.23 \n",
" 5.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 39 \n",
" 31.27 \n",
" 5.00 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 142 \n",
" 41.19 \n",
" 5.00 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 5 \n",
" \n",
" \n",
" 143 \n",
" 27.05 \n",
" 5.00 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 6 \n",
" \n",
" \n",
" 156 \n",
" 48.17 \n",
" 5.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 6 \n",
" \n",
" \n",
" 185 \n",
" 20.69 \n",
" 5.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 5 \n",
" \n",
" \n",
" 11 \n",
" 35.26 \n",
" 5.00 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 83 \n",
" 32.68 \n",
" 5.00 \n",
" Male \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 197 \n",
" 43.11 \n",
" 5.00 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 4 \n",
" \n",
" \n",
" 73 \n",
" 25.28 \n",
" 5.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 116 \n",
" 29.93 \n",
" 5.07 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 155 \n",
" 29.85 \n",
" 5.14 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 5 \n",
" \n",
" \n",
" 172 \n",
" 7.25 \n",
" 5.15 \n",
" Male \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 211 \n",
" 25.89 \n",
" 5.16 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 85 \n",
" 34.83 \n",
" 5.17 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 4 \n",
" \n",
" \n",
" 52 \n",
" 34.81 \n",
" 5.20 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 44 \n",
" 30.40 \n",
" 5.60 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 181 \n",
" 23.33 \n",
" 5.65 \n",
" Male \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 88 \n",
" 24.71 \n",
" 5.85 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" \n",
" \n",
" 239 \n",
" 29.03 \n",
" 5.92 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 47 \n",
" 32.40 \n",
" 6.00 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 183 \n",
" 23.17 \n",
" 6.50 \n",
" Male \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 214 \n",
" 28.17 \n",
" 6.50 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 141 \n",
" 34.30 \n",
" 6.70 \n",
" Male \n",
" No \n",
" Thur \n",
" Lunch \n",
" 6 \n",
" \n",
" \n",
" 59 \n",
" 48.27 \n",
" 6.73 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 23 \n",
" 39.42 \n",
" 7.58 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 212 \n",
" 48.33 \n",
" 9.00 \n",
" Male \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
" 170 \n",
" 50.81 \n",
" 10.00 \n",
" Male \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
"
\n",
"
244 rows × 7 columns
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size\n",
"67 3.07 1.00 Female Yes Sat Dinner 1\n",
"236 12.60 1.00 Male Yes Sat Dinner 2\n",
"92 5.75 1.00 Female Yes Fri Dinner 2\n",
"111 7.25 1.00 Female No Sat Dinner 1\n",
"0 16.99 1.01 Female No Sun Dinner 2\n",
"215 12.90 1.10 Female Yes Sat Dinner 2\n",
"237 32.83 1.17 Male Yes Sat Dinner 2\n",
"235 10.07 1.25 Male No Sat Dinner 2\n",
"75 10.51 1.25 Male No Sat Dinner 2\n",
"135 8.51 1.25 Female No Thur Lunch 2\n",
"43 9.68 1.32 Male No Sun Dinner 2\n",
"146 18.64 1.36 Female No Thur Lunch 3\n",
"218 7.74 1.44 Male Yes Sat Dinner 2\n",
"195 7.56 1.44 Male No Thur Lunch 2\n",
"30 9.55 1.45 Male No Sat Dinner 2\n",
"233 10.77 1.47 Male No Sat Dinner 2\n",
"126 8.52 1.48 Male No Thur Lunch 2\n",
"190 15.69 1.50 Male Yes Sun Dinner 2\n",
"57 26.41 1.50 Female No Sat Dinner 2\n",
"97 12.03 1.50 Male Yes Fri Dinner 2\n",
"99 12.46 1.50 Male No Fri Dinner 2\n",
"117 10.65 1.50 Female No Thur Lunch 2\n",
"132 11.17 1.50 Female No Thur Lunch 2\n",
"217 11.59 1.50 Male Yes Sat Dinner 2\n",
"145 8.35 1.50 Female No Thur Lunch 2\n",
"130 19.08 1.50 Male No Thur Lunch 2\n",
"53 9.94 1.56 Male No Sun Dinner 2\n",
"12 15.42 1.57 Male No Sun Dinner 2\n",
"224 13.42 1.58 Male Yes Fri Lunch 2\n",
"168 10.59 1.61 Female Yes Sat Dinner 2\n",
".. ... ... ... ... ... ... ...\n",
"5 25.29 4.71 Male No Sun Dinner 4\n",
"95 40.17 4.73 Male Yes Fri Dinner 4\n",
"46 22.23 5.00 Male No Sun Dinner 2\n",
"39 31.27 5.00 Male No Sat Dinner 3\n",
"142 41.19 5.00 Male No Thur Lunch 5\n",
"143 27.05 5.00 Female No Thur Lunch 6\n",
"156 48.17 5.00 Male No Sun Dinner 6\n",
"185 20.69 5.00 Male No Sun Dinner 5\n",
"11 35.26 5.00 Female No Sun Dinner 4\n",
"83 32.68 5.00 Male Yes Thur Lunch 2\n",
"197 43.11 5.00 Female Yes Thur Lunch 4\n",
"73 25.28 5.00 Female Yes Sat Dinner 2\n",
"116 29.93 5.07 Male No Sun Dinner 4\n",
"155 29.85 5.14 Female No Sun Dinner 5\n",
"172 7.25 5.15 Male Yes Sun Dinner 2\n",
"211 25.89 5.16 Male Yes Sat Dinner 4\n",
"85 34.83 5.17 Female No Thur Lunch 4\n",
"52 34.81 5.20 Female No Sun Dinner 4\n",
"44 30.40 5.60 Male No Sun Dinner 4\n",
"181 23.33 5.65 Male Yes Sun Dinner 2\n",
"88 24.71 5.85 Male No Thur Lunch 2\n",
"239 29.03 5.92 Male No Sat Dinner 3\n",
"47 32.40 6.00 Male No Sun Dinner 4\n",
"183 23.17 6.50 Male Yes Sun Dinner 4\n",
"214 28.17 6.50 Female Yes Sat Dinner 3\n",
"141 34.30 6.70 Male No Thur Lunch 6\n",
"59 48.27 6.73 Male No Sat Dinner 4\n",
"23 39.42 7.58 Male No Sat Dinner 4\n",
"212 48.33 9.00 Male No Sat Dinner 4\n",
"170 50.81 10.00 Male Yes Sat Dinner 3\n",
"\n",
"[244 rows x 7 columns]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.sort_values('tip')"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size\n",
"0 16.99 1.01 Female No Sun Dinner 2\n",
"1 10.34 1.66 Male No Sun Dinner 3\n",
"2 21.01 3.50 Male No Sun Dinner 3\n",
"3 23.68 3.31 Male No Sun Dinner 2\n",
"4 24.59 3.61 Female No Sun Dinner 4"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"0 1.01\n",
"1 1.66\n",
"2 3.50\n",
"3 3.31\n",
"4 3.61\n",
"5 4.71\n",
"6 2.00\n",
"7 3.12\n",
"8 1.96\n",
"9 3.23\n",
"10 1.71\n",
"11 5.00\n",
"12 1.57\n",
"13 3.00\n",
"14 3.02\n",
"15 3.92\n",
"16 1.67\n",
"17 3.71\n",
"18 3.50\n",
"19 3.35\n",
"20 4.08\n",
"21 2.75\n",
"22 2.23\n",
"23 7.58\n",
"24 3.18\n",
"25 2.34\n",
"26 2.00\n",
"27 2.00\n",
"28 4.30\n",
"29 3.00\n",
" ... \n",
"214 6.50\n",
"215 1.10\n",
"216 3.00\n",
"217 1.50\n",
"218 1.44\n",
"219 3.09\n",
"220 2.20\n",
"221 3.48\n",
"222 1.92\n",
"223 3.00\n",
"224 1.58\n",
"225 2.50\n",
"226 2.00\n",
"227 3.00\n",
"228 2.72\n",
"229 2.88\n",
"230 2.00\n",
"231 3.00\n",
"232 3.39\n",
"233 1.47\n",
"234 3.00\n",
"235 1.25\n",
"236 1.00\n",
"237 1.17\n",
"238 4.67\n",
"239 5.92\n",
"240 2.00\n",
"241 2.00\n",
"242 1.75\n",
"243 3.00\n",
"Name: tip, Length: 244, dtype: float64"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data['tip']"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"0 0.059447\n",
"1 0.160542\n",
"2 0.166587\n",
"3 0.139780\n",
"4 0.146808\n",
"5 0.186240\n",
"6 0.228050\n",
"7 0.116071\n",
"8 0.130319\n",
"9 0.218539\n",
"10 0.166504\n",
"11 0.141804\n",
"12 0.101816\n",
"13 0.162778\n",
"14 0.203641\n",
"15 0.181650\n",
"16 0.161665\n",
"17 0.227747\n",
"18 0.206246\n",
"19 0.162228\n",
"20 0.227679\n",
"21 0.135535\n",
"22 0.141408\n",
"23 0.192288\n",
"24 0.160444\n",
"25 0.131387\n",
"26 0.149589\n",
"27 0.157604\n",
"28 0.198157\n",
"29 0.152672\n",
" ... \n",
"214 0.230742\n",
"215 0.085271\n",
"216 0.106572\n",
"217 0.129422\n",
"218 0.186047\n",
"219 0.102522\n",
"220 0.180921\n",
"221 0.259314\n",
"222 0.223776\n",
"223 0.187735\n",
"224 0.117735\n",
"225 0.153657\n",
"226 0.198216\n",
"227 0.146699\n",
"228 0.204819\n",
"229 0.130199\n",
"230 0.083299\n",
"231 0.191205\n",
"232 0.291990\n",
"233 0.136490\n",
"234 0.193175\n",
"235 0.124131\n",
"236 0.079365\n",
"237 0.035638\n",
"238 0.130338\n",
"239 0.203927\n",
"240 0.073584\n",
"241 0.088222\n",
"242 0.098204\n",
"243 0.159744\n",
"Length: 244, dtype: float64"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data['tip'] / data['total_bill']"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"data['perc_tip'] = data['tip'] / data['total_bill']"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" perc_tip \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.059447 \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.160542 \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.166587 \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.139780 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.146808 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size perc_tip\n",
"0 16.99 1.01 Female No Sun Dinner 2 0.059447\n",
"1 10.34 1.66 Male No Sun Dinner 3 0.160542\n",
"2 21.01 3.50 Male No Sun Dinner 3 0.166587\n",
"3 23.68 3.31 Male No Sun Dinner 2 0.139780\n",
"4 24.59 3.61 Female No Sun Dinner 4 0.146808"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" perc_tip \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.059447 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.146808 \n",
" \n",
" \n",
" 11 \n",
" 35.26 \n",
" 5.00 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.141804 \n",
" \n",
" \n",
" 14 \n",
" 14.83 \n",
" 3.02 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.203641 \n",
" \n",
" \n",
" 16 \n",
" 10.33 \n",
" 1.67 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.161665 \n",
" \n",
" \n",
" 18 \n",
" 16.97 \n",
" 3.50 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.206246 \n",
" \n",
" \n",
" 21 \n",
" 20.29 \n",
" 2.75 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.135535 \n",
" \n",
" \n",
" 22 \n",
" 15.77 \n",
" 2.23 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.141408 \n",
" \n",
" \n",
" 29 \n",
" 19.65 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.152672 \n",
" \n",
" \n",
" 32 \n",
" 15.06 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.199203 \n",
" \n",
" \n",
" 33 \n",
" 20.69 \n",
" 2.45 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" 0.118415 \n",
" \n",
" \n",
" 37 \n",
" 16.93 \n",
" 3.07 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" 0.181335 \n",
" \n",
" \n",
" 51 \n",
" 10.29 \n",
" 2.60 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.252672 \n",
" \n",
" \n",
" 52 \n",
" 34.81 \n",
" 5.20 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.149382 \n",
" \n",
" \n",
" 57 \n",
" 26.41 \n",
" 1.50 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.056797 \n",
" \n",
" \n",
" 66 \n",
" 16.45 \n",
" 2.47 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.150152 \n",
" \n",
" \n",
" 67 \n",
" 3.07 \n",
" 1.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 1 \n",
" 0.325733 \n",
" \n",
" \n",
" 71 \n",
" 17.07 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" 0.175747 \n",
" \n",
" \n",
" 72 \n",
" 26.86 \n",
" 3.14 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.116902 \n",
" \n",
" \n",
" 73 \n",
" 25.28 \n",
" 5.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.197785 \n",
" \n",
" \n",
" 74 \n",
" 14.73 \n",
" 2.20 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.149355 \n",
" \n",
" \n",
" 82 \n",
" 10.07 \n",
" 1.83 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 1 \n",
" 0.181728 \n",
" \n",
" \n",
" 85 \n",
" 34.83 \n",
" 5.17 \n",
" Female \n",
" No \n",
" Thur \n",
" Lunch \n",
" 4 \n",
" 0.148435 \n",
" \n",
" \n",
" 92 \n",
" 5.75 \n",
" 1.00 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" 0.173913 \n",
" \n",
" \n",
" 93 \n",
" 16.32 \n",
" 4.30 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" 0.263480 \n",
" \n",
" \n",
" 94 \n",
" 22.75 \n",
" 3.25 \n",
" Female \n",
" No \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" 0.142857 \n",
" \n",
" \n",
" 100 \n",
" 11.35 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" 0.220264 \n",
" \n",
" \n",
" 101 \n",
" 15.38 \n",
" 3.00 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Dinner \n",
" 2 \n",
" 0.195059 \n",
" \n",
" \n",
" 102 \n",
" 44.30 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" 0.056433 \n",
" \n",
" \n",
" 103 \n",
" 22.42 \n",
" 3.48 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.155219 \n",
" \n",
" \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" ... \n",
" \n",
" \n",
" 155 \n",
" 29.85 \n",
" 5.14 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 5 \n",
" 0.172194 \n",
" \n",
" \n",
" 157 \n",
" 25.00 \n",
" 3.75 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.150000 \n",
" \n",
" \n",
" 158 \n",
" 13.39 \n",
" 2.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.194922 \n",
" \n",
" \n",
" 162 \n",
" 16.21 \n",
" 2.00 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.123381 \n",
" \n",
" \n",
" 164 \n",
" 17.51 \n",
" 3.00 \n",
" Female \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.171331 \n",
" \n",
" \n",
" 168 \n",
" 10.59 \n",
" 1.61 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.152030 \n",
" \n",
" \n",
" 169 \n",
" 10.63 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.188147 \n",
" \n",
" \n",
" 178 \n",
" 9.60 \n",
" 4.00 \n",
" Female \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.416667 \n",
" \n",
" \n",
" 186 \n",
" 20.90 \n",
" 3.50 \n",
" Female \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.167464 \n",
" \n",
" \n",
" 188 \n",
" 18.15 \n",
" 3.50 \n",
" Female \n",
" Yes \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.192837 \n",
" \n",
" \n",
" 191 \n",
" 19.81 \n",
" 4.19 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" 0.211509 \n",
" \n",
" \n",
" 197 \n",
" 43.11 \n",
" 5.00 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 4 \n",
" 0.115982 \n",
" \n",
" \n",
" 198 \n",
" 13.00 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" 0.153846 \n",
" \n",
" \n",
" 201 \n",
" 12.74 \n",
" 2.01 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" 0.157771 \n",
" \n",
" \n",
" 202 \n",
" 13.00 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" 0.153846 \n",
" \n",
" \n",
" 203 \n",
" 16.40 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 2 \n",
" 0.152439 \n",
" \n",
" \n",
" 205 \n",
" 16.47 \n",
" 3.23 \n",
" Female \n",
" Yes \n",
" Thur \n",
" Lunch \n",
" 3 \n",
" 0.196114 \n",
" \n",
" \n",
" 209 \n",
" 12.76 \n",
" 2.23 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.174765 \n",
" \n",
" \n",
" 213 \n",
" 13.27 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.188395 \n",
" \n",
" \n",
" 214 \n",
" 28.17 \n",
" 6.50 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" 0.230742 \n",
" \n",
" \n",
" 215 \n",
" 12.90 \n",
" 1.10 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.085271 \n",
" \n",
" \n",
" 219 \n",
" 30.14 \n",
" 3.09 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 4 \n",
" 0.102522 \n",
" \n",
" \n",
" 221 \n",
" 13.42 \n",
" 3.48 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" 0.259314 \n",
" \n",
" \n",
" 223 \n",
" 15.98 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Fri \n",
" Lunch \n",
" 3 \n",
" 0.187735 \n",
" \n",
" \n",
" 225 \n",
" 16.27 \n",
" 2.50 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" 0.153657 \n",
" \n",
" \n",
" 226 \n",
" 10.09 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Fri \n",
" Lunch \n",
" 2 \n",
" 0.198216 \n",
" \n",
" \n",
" 229 \n",
" 22.12 \n",
" 2.88 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.130199 \n",
" \n",
" \n",
" 238 \n",
" 35.83 \n",
" 4.67 \n",
" Female \n",
" No \n",
" Sat \n",
" Dinner \n",
" 3 \n",
" 0.130338 \n",
" \n",
" \n",
" 240 \n",
" 27.18 \n",
" 2.00 \n",
" Female \n",
" Yes \n",
" Sat \n",
" Dinner \n",
" 2 \n",
" 0.073584 \n",
" \n",
" \n",
" 243 \n",
" 18.78 \n",
" 3.00 \n",
" Female \n",
" No \n",
" Thur \n",
" Dinner \n",
" 2 \n",
" 0.159744 \n",
" \n",
" \n",
"
\n",
"
87 rows × 8 columns
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size perc_tip\n",
"0 16.99 1.01 Female No Sun Dinner 2 0.059447\n",
"4 24.59 3.61 Female No Sun Dinner 4 0.146808\n",
"11 35.26 5.00 Female No Sun Dinner 4 0.141804\n",
"14 14.83 3.02 Female No Sun Dinner 2 0.203641\n",
"16 10.33 1.67 Female No Sun Dinner 3 0.161665\n",
"18 16.97 3.50 Female No Sun Dinner 3 0.206246\n",
"21 20.29 2.75 Female No Sat Dinner 2 0.135535\n",
"22 15.77 2.23 Female No Sat Dinner 2 0.141408\n",
"29 19.65 3.00 Female No Sat Dinner 2 0.152672\n",
"32 15.06 3.00 Female No Sat Dinner 2 0.199203\n",
"33 20.69 2.45 Female No Sat Dinner 4 0.118415\n",
"37 16.93 3.07 Female No Sat Dinner 3 0.181335\n",
"51 10.29 2.60 Female No Sun Dinner 2 0.252672\n",
"52 34.81 5.20 Female No Sun Dinner 4 0.149382\n",
"57 26.41 1.50 Female No Sat Dinner 2 0.056797\n",
"66 16.45 2.47 Female No Sat Dinner 2 0.150152\n",
"67 3.07 1.00 Female Yes Sat Dinner 1 0.325733\n",
"71 17.07 3.00 Female No Sat Dinner 3 0.175747\n",
"72 26.86 3.14 Female Yes Sat Dinner 2 0.116902\n",
"73 25.28 5.00 Female Yes Sat Dinner 2 0.197785\n",
"74 14.73 2.20 Female No Sat Dinner 2 0.149355\n",
"82 10.07 1.83 Female No Thur Lunch 1 0.181728\n",
"85 34.83 5.17 Female No Thur Lunch 4 0.148435\n",
"92 5.75 1.00 Female Yes Fri Dinner 2 0.173913\n",
"93 16.32 4.30 Female Yes Fri Dinner 2 0.263480\n",
"94 22.75 3.25 Female No Fri Dinner 2 0.142857\n",
"100 11.35 2.50 Female Yes Fri Dinner 2 0.220264\n",
"101 15.38 3.00 Female Yes Fri Dinner 2 0.195059\n",
"102 44.30 2.50 Female Yes Sat Dinner 3 0.056433\n",
"103 22.42 3.48 Female Yes Sat Dinner 2 0.155219\n",
".. ... ... ... ... ... ... ... ...\n",
"155 29.85 5.14 Female No Sun Dinner 5 0.172194\n",
"157 25.00 3.75 Female No Sun Dinner 4 0.150000\n",
"158 13.39 2.61 Female No Sun Dinner 2 0.194922\n",
"162 16.21 2.00 Female No Sun Dinner 3 0.123381\n",
"164 17.51 3.00 Female Yes Sun Dinner 2 0.171331\n",
"168 10.59 1.61 Female Yes Sat Dinner 2 0.152030\n",
"169 10.63 2.00 Female Yes Sat Dinner 2 0.188147\n",
"178 9.60 4.00 Female Yes Sun Dinner 2 0.416667\n",
"186 20.90 3.50 Female Yes Sun Dinner 3 0.167464\n",
"188 18.15 3.50 Female Yes Sun Dinner 3 0.192837\n",
"191 19.81 4.19 Female Yes Thur Lunch 2 0.211509\n",
"197 43.11 5.00 Female Yes Thur Lunch 4 0.115982\n",
"198 13.00 2.00 Female Yes Thur Lunch 2 0.153846\n",
"201 12.74 2.01 Female Yes Thur Lunch 2 0.157771\n",
"202 13.00 2.00 Female Yes Thur Lunch 2 0.153846\n",
"203 16.40 2.50 Female Yes Thur Lunch 2 0.152439\n",
"205 16.47 3.23 Female Yes Thur Lunch 3 0.196114\n",
"209 12.76 2.23 Female Yes Sat Dinner 2 0.174765\n",
"213 13.27 2.50 Female Yes Sat Dinner 2 0.188395\n",
"214 28.17 6.50 Female Yes Sat Dinner 3 0.230742\n",
"215 12.90 1.10 Female Yes Sat Dinner 2 0.085271\n",
"219 30.14 3.09 Female Yes Sat Dinner 4 0.102522\n",
"221 13.42 3.48 Female Yes Fri Lunch 2 0.259314\n",
"223 15.98 3.00 Female No Fri Lunch 3 0.187735\n",
"225 16.27 2.50 Female Yes Fri Lunch 2 0.153657\n",
"226 10.09 2.00 Female Yes Fri Lunch 2 0.198216\n",
"229 22.12 2.88 Female Yes Sat Dinner 2 0.130199\n",
"238 35.83 4.67 Female No Sat Dinner 3 0.130338\n",
"240 27.18 2.00 Female Yes Sat Dinner 2 0.073584\n",
"243 18.78 3.00 Female No Thur Dinner 2 0.159744\n",
"\n",
"[87 rows x 8 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data[data.sex == 'Female']"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"data[data.sex == 'Female'].to_csv('waitresses.csv')"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
",total_bill,tip,sex,smoker,day,time,size,perc_tip\r\n",
"0,16.99,1.01,Female,No,Sun,Dinner,2,0.05944673337257211\r\n",
"4,24.59,3.61,Female,No,Sun,Dinner,4,0.14680764538430255\r\n",
"11,35.26,5.0,Female,No,Sun,Dinner,4,0.14180374361883155\r\n",
"14,14.83,3.02,Female,No,Sun,Dinner,2,0.20364126770060686\r\n",
"16,10.33,1.67,Female,No,Sun,Dinner,3,0.1616650532429816\r\n",
"18,16.97,3.5,Female,No,Sun,Dinner,3,0.20624631703005306\r\n",
"21,20.29,2.75,Female,No,Sat,Dinner,2,0.13553474618038444\r\n",
"22,15.77,2.23,Female,No,Sat,Dinner,2,0.14140773620798985\r\n",
"29,19.65,3.0,Female,No,Sat,Dinner,2,0.15267175572519084\r\n",
"32,15.06,3.0,Female,No,Sat,Dinner,2,0.199203187250996\r\n",
"33,20.69,2.45,Female,No,Sat,Dinner,4,0.11841469308844853\r\n",
"37,16.93,3.07,Female,No,Sat,Dinner,3,0.1813349084465446\r\n",
"51,10.29,2.6,Female,No,Sun,Dinner,2,0.2526724975704568\r\n",
"52,34.81,5.2,Female,No,Sun,Dinner,4,0.14938236139040506\r\n",
"57,26.41,1.5,Female,No,Sat,Dinner,2,0.05679666792881484\r\n",
"66,16.45,2.47,Female,No,Sat,Dinner,2,0.1501519756838906\r\n",
"67,3.07,1.0,Female,Yes,Sat,Dinner,1,0.32573289902280134\r\n",
"71,17.07,3.0,Female,No,Sat,Dinner,3,0.1757469244288225\r\n",
"72,26.86,3.14,Female,Yes,Sat,Dinner,2,0.11690245718540582\r\n",
"73,25.28,5.0,Female,Yes,Sat,Dinner,2,0.19778481012658228\r\n",
"74,14.73,2.2,Female,No,Sat,Dinner,2,0.14935505770536323\r\n",
"82,10.07,1.83,Female,No,Thur,Lunch,1,0.1817279046673287\r\n",
"85,34.83,5.17,Female,No,Thur,Lunch,4,0.14843525696238874\r\n",
"92,5.75,1.0,Female,Yes,Fri,Dinner,2,0.17391304347826086\r\n",
"93,16.32,4.3,Female,Yes,Fri,Dinner,2,0.26348039215686275\r\n",
"94,22.75,3.25,Female,No,Fri,Dinner,2,0.14285714285714285\r\n",
"100,11.35,2.5,Female,Yes,Fri,Dinner,2,0.22026431718061676\r\n",
"101,15.38,3.0,Female,Yes,Fri,Dinner,2,0.19505851755526657\r\n",
"102,44.3,2.5,Female,Yes,Sat,Dinner,3,0.05643340857787811\r\n",
"103,22.42,3.48,Female,Yes,Sat,Dinner,2,0.15521855486173058\r\n",
"104,20.92,4.08,Female,No,Sat,Dinner,2,0.1950286806883365\r\n",
"109,14.31,4.0,Female,Yes,Sat,Dinner,2,0.2795248078266946\r\n",
"111,7.25,1.0,Female,No,Sat,Dinner,1,0.13793103448275862\r\n",
"114,25.71,4.0,Female,No,Sun,Dinner,3,0.15558148580318942\r\n",
"115,17.31,3.5,Female,No,Sun,Dinner,2,0.20219526285384173\r\n",
"117,10.65,1.5,Female,No,Thur,Lunch,2,0.14084507042253522\r\n",
"118,12.43,1.8,Female,No,Thur,Lunch,2,0.14481094127111827\r\n",
"119,24.08,2.92,Female,No,Thur,Lunch,4,0.1212624584717608\r\n",
"121,13.42,1.68,Female,No,Thur,Lunch,2,0.12518628912071533\r\n",
"124,12.48,2.52,Female,No,Thur,Lunch,2,0.20192307692307693\r\n",
"125,29.8,4.2,Female,No,Thur,Lunch,6,0.14093959731543623\r\n",
"127,14.52,2.0,Female,No,Thur,Lunch,2,0.13774104683195593\r\n",
"128,11.38,2.0,Female,No,Thur,Lunch,2,0.17574692442882248\r\n",
"131,20.27,2.83,Female,No,Thur,Lunch,2,0.13961519486926494\r\n",
"132,11.17,1.5,Female,No,Thur,Lunch,2,0.13428827215756492\r\n",
"133,12.26,2.0,Female,No,Thur,Lunch,2,0.1631321370309951\r\n",
"134,18.26,3.25,Female,No,Thur,Lunch,2,0.17798466593647316\r\n",
"135,8.51,1.25,Female,No,Thur,Lunch,2,0.14688601645123384\r\n",
"136,10.33,2.0,Female,No,Thur,Lunch,2,0.1936108422071636\r\n",
"137,14.15,2.0,Female,No,Thur,Lunch,2,0.1413427561837456\r\n",
"139,13.16,2.75,Female,No,Thur,Lunch,2,0.20896656534954408\r\n",
"140,17.47,3.5,Female,No,Thur,Lunch,2,0.20034344590726963\r\n",
"143,27.05,5.0,Female,No,Thur,Lunch,6,0.18484288354898337\r\n",
"144,16.43,2.3,Female,No,Thur,Lunch,2,0.1399878271454656\r\n",
"145,8.35,1.5,Female,No,Thur,Lunch,2,0.17964071856287425\r\n",
"146,18.64,1.36,Female,No,Thur,Lunch,3,0.07296137339055794\r\n",
"147,11.87,1.63,Female,No,Thur,Lunch,2,0.13732097725358045\r\n",
"155,29.85,5.14,Female,No,Sun,Dinner,5,0.1721943048576214\r\n",
"157,25.0,3.75,Female,No,Sun,Dinner,4,0.15\r\n",
"158,13.39,2.61,Female,No,Sun,Dinner,2,0.19492158327109782\r\n",
"162,16.21,2.0,Female,No,Sun,Dinner,3,0.12338062924120913\r\n",
"164,17.51,3.0,Female,Yes,Sun,Dinner,2,0.17133066818960593\r\n",
"168,10.59,1.61,Female,Yes,Sat,Dinner,2,0.15203021718602455\r\n",
"169,10.63,2.0,Female,Yes,Sat,Dinner,2,0.18814675446848542\r\n",
"178,9.6,4.0,Female,Yes,Sun,Dinner,2,0.4166666666666667\r\n",
"186,20.9,3.5,Female,Yes,Sun,Dinner,3,0.1674641148325359\r\n",
"188,18.15,3.5,Female,Yes,Sun,Dinner,3,0.1928374655647383\r\n",
"191,19.81,4.19,Female,Yes,Thur,Lunch,2,0.21150933871781932\r\n",
"197,43.11,5.0,Female,Yes,Thur,Lunch,4,0.1159823706796567\r\n",
"198,13.0,2.0,Female,Yes,Thur,Lunch,2,0.15384615384615385\r\n",
"201,12.74,2.01,Female,Yes,Thur,Lunch,2,0.15777080062794346\r\n",
"202,13.0,2.0,Female,Yes,Thur,Lunch,2,0.15384615384615385\r\n",
"203,16.4,2.5,Female,Yes,Thur,Lunch,2,0.15243902439024393\r\n",
"205,16.47,3.23,Female,Yes,Thur,Lunch,3,0.19611414693381907\r\n",
"209,12.76,2.23,Female,Yes,Sat,Dinner,2,0.17476489028213166\r\n",
"213,13.27,2.5,Female,Yes,Sat,Dinner,2,0.18839487565938207\r\n",
"214,28.17,6.5,Female,Yes,Sat,Dinner,3,0.23074192403265883\r\n",
"215,12.9,1.1,Female,Yes,Sat,Dinner,2,0.08527131782945736\r\n",
"219,30.14,3.09,Female,Yes,Sat,Dinner,4,0.10252156602521566\r\n",
"221,13.42,3.48,Female,Yes,Fri,Lunch,2,0.2593144560357675\r\n",
"223,15.98,3.0,Female,No,Fri,Lunch,3,0.18773466833541927\r\n",
"225,16.27,2.5,Female,Yes,Fri,Lunch,2,0.15365703749231716\r\n",
"226,10.09,2.0,Female,Yes,Fri,Lunch,2,0.19821605550049554\r\n",
"229,22.12,2.88,Female,Yes,Sat,Dinner,2,0.13019891500904157\r\n",
"238,35.83,4.67,Female,No,Sat,Dinner,3,0.13033770583310075\r\n",
"240,27.18,2.0,Female,Yes,Sat,Dinner,2,0.07358351729212656\r\n",
"243,18.78,3.0,Female,No,Thur,Dinner,2,0.1597444089456869\r\n"
]
}
],
"source": [
"!cat waitresses.csv"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.16080258172250478"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data['perc_tip'].mean()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Slow version:\n",
"#the_sum = 0\n",
"#for row in data:\n",
"# the_sum += row['perc_tip']\n",
"#\n",
"#the_mean = the_sum / len(data)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"size\n",
"1 0.217292\n",
"2 0.165719\n",
"3 0.152157\n",
"4 0.145949\n",
"5 0.141495\n",
"6 0.156229\n",
"Name: perc_tip, dtype: float64"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.groupby('size')['perc_tip'].mean()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"size sex \n",
"1 Female 0.215131\n",
" Male 0.223776\n",
"2 Female 0.170830\n",
" Male 0.162694\n",
"3 Female 0.159899\n",
" Male 0.147641\n",
"4 Female 0.132734\n",
" Male 0.150197\n",
"5 Female 0.172194\n",
" Male 0.133821\n",
"6 Female 0.162891\n",
" Male 0.149567\n",
"Name: perc_tip, dtype: float64"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.groupby(['size', 'sex'])['perc_tip'].mean()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"means = data.groupby(['size', 'sex'])['perc_tip'].mean()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" sex \n",
" Female \n",
" Male \n",
" \n",
" \n",
" size \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" \n",
" 1 \n",
" 0.215131 \n",
" 0.223776 \n",
" \n",
" \n",
" 2 \n",
" 0.170830 \n",
" 0.162694 \n",
" \n",
" \n",
" 3 \n",
" 0.159899 \n",
" 0.147641 \n",
" \n",
" \n",
" 4 \n",
" 0.132734 \n",
" 0.150197 \n",
" \n",
" \n",
" 5 \n",
" 0.172194 \n",
" 0.133821 \n",
" \n",
" \n",
" 6 \n",
" 0.162891 \n",
" 0.149567 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
"sex Female Male\n",
"size \n",
"1 0.215131 0.223776\n",
"2 0.170830 0.162694\n",
"3 0.159899 0.147641\n",
"4 0.132734 0.150197\n",
"5 0.172194 0.133821\n",
"6 0.162891 0.149567"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"means.unstack('sex')"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\\\begin{tabular}{lrr}\\n\\\\toprule\\nsex & Female & Male \\\\\\\\\\nsize & & \\\\\\\\\\n\\\\midrule\\n1 & 0.215131 & 0.223776 \\\\\\\\\\n2 & 0.170830 & 0.162694 \\\\\\\\\\n3 & 0.159899 & 0.147641 \\\\\\\\\\n4 & 0.132734 & 0.150197 \\\\\\\\\\n5 & 0.172194 & 0.133821 \\\\\\\\\\n6 & 0.162891 & 0.149567 \\\\\\\\\\n\\\\bottomrule\\n\\\\end{tabular}\\n'"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.groupby(['size', 'sex'])['perc_tip'].mean().unstack().to_latex()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\\\begin{tabular}{lrr}\\n\\\\toprule\\nsex & Female & Male \\\\\\\\\\nsize & & \\\\\\\\\\n\\\\midrule\\n1 & 0.215131 & 0.223776 \\\\\\\\\\n2 & 0.170830 & 0.162694 \\\\\\\\\\n3 & 0.159899 & 0.147641 \\\\\\\\\\n4 & 0.132734 & 0.150197 \\\\\\\\\\n5 & 0.172194 & 0.133821 \\\\\\\\\\n6 & 0.162891 & 0.149567 \\\\\\\\\\n\\\\bottomrule\\n\\\\end{tabular}\\n'"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# \"readable\" version:\n",
"(data\n",
" .groupby(['size', 'sex'])\n",
" ['perc_tip']\n",
" .mean()\n",
" .unstack()\n",
" .to_latex())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# $\\to$ Slide"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# matplotlib: visualize data"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"from matplotlib import pyplot as plt\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[]"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.plot([1,3,2])"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.bar([0,1,2], [1,3,2])"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 26,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data['total_bill'].plot()"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data[['total_bill', 'tip']].plot()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data.groupby('size')['perc_tip'].mean().plot(kind='bar')"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"data.groupby(['size', 'sex'])['perc_tip'].mean().unstack().plot(kind='bar')"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 30,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"female = (data['sex'] == 'Female')\n",
"data.plot(kind='scatter', x='perc_tip', y='total_bill',\n",
" c=female, edgecolor='r'\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# $\\to$ Slide"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Statsmodels"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/pietro/.local/lib/python3.5/site-packages/statsmodels/compat/pandas.py:56: FutureWarning: The pandas.core.datetools module is deprecated and will be removed in a future version. Please use the pandas.tseries module instead.\n",
" from pandas.core import datetools\n"
]
}
],
"source": [
"import statsmodels.api as sm"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"res = sm.OLS.from_formula('tip ~ total_bill + sex + day + size', data=data).fit()"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"OLS Regression Results \n",
"\n",
" Dep. Variable: tip R-squared: 0.469 \n",
" \n",
"\n",
" Model: OLS Adj. R-squared: 0.456 \n",
" \n",
"\n",
" Method: Least Squares F-statistic: 34.93 \n",
" \n",
"\n",
" Date: Sat, 05 May 2018 Prob (F-statistic): 4.04e-30 \n",
" \n",
"\n",
" Time: 14:52:28 Log-Likelihood: -347.66 \n",
" \n",
"\n",
" No. Observations: 244 AIC: 709.3 \n",
" \n",
"\n",
" Df Residuals: 237 BIC: 733.8 \n",
" \n",
"\n",
" Df Model: 6 \n",
" \n",
"\n",
" Covariance Type: nonrobust \n",
" \n",
"
\n",
"\n",
"\n",
" coef std err t P>|t| [0.025 0.975] \n",
" \n",
"\n",
" Intercept 0.7601 0.289 2.633 0.009 0.191 1.329 \n",
" \n",
"\n",
" sex[T.Male] -0.0326 0.141 -0.231 0.818 -0.311 0.245 \n",
" \n",
"\n",
" day[T.Sat] -0.1202 0.261 -0.461 0.645 -0.634 0.394 \n",
" \n",
"\n",
" day[T.Sun] -0.0064 0.269 -0.024 0.981 -0.536 0.523 \n",
" \n",
"\n",
" day[T.Thur] -0.0789 0.269 -0.293 0.770 -0.609 0.451 \n",
" \n",
"\n",
" total_bill 0.0932 0.009 10.019 0.000 0.075 0.112 \n",
" \n",
"\n",
" size 0.1867 0.087 2.137 0.034 0.015 0.359 \n",
" \n",
"
\n",
"\n",
"\n",
" Omnibus: 26.163 Durbin-Watson: 2.094 \n",
" \n",
"\n",
" Prob(Omnibus): 0.000 Jarque-Bera (JB): 49.406 \n",
" \n",
"\n",
" Skew: 0.571 Prob(JB): 1.87e-11 \n",
" \n",
"\n",
" Kurtosis: 4.886 Cond. No. 161. \n",
" \n",
"
"
],
"text/plain": [
"\n",
"\"\"\"\n",
" OLS Regression Results \n",
"==============================================================================\n",
"Dep. Variable: tip R-squared: 0.469\n",
"Model: OLS Adj. R-squared: 0.456\n",
"Method: Least Squares F-statistic: 34.93\n",
"Date: Sat, 05 May 2018 Prob (F-statistic): 4.04e-30\n",
"Time: 14:52:28 Log-Likelihood: -347.66\n",
"No. Observations: 244 AIC: 709.3\n",
"Df Residuals: 237 BIC: 733.8\n",
"Df Model: 6 \n",
"Covariance Type: nonrobust \n",
"===============================================================================\n",
" coef std err t P>|t| [0.025 0.975]\n",
"-------------------------------------------------------------------------------\n",
"Intercept 0.7601 0.289 2.633 0.009 0.191 1.329\n",
"sex[T.Male] -0.0326 0.141 -0.231 0.818 -0.311 0.245\n",
"day[T.Sat] -0.1202 0.261 -0.461 0.645 -0.634 0.394\n",
"day[T.Sun] -0.0064 0.269 -0.024 0.981 -0.536 0.523\n",
"day[T.Thur] -0.0789 0.269 -0.293 0.770 -0.609 0.451\n",
"total_bill 0.0932 0.009 10.019 0.000 0.075 0.112\n",
"size 0.1867 0.087 2.137 0.034 0.015 0.359\n",
"==============================================================================\n",
"Omnibus: 26.163 Durbin-Watson: 2.094\n",
"Prob(Omnibus): 0.000 Jarque-Bera (JB): 49.406\n",
"Skew: 0.571 Prob(JB): 1.87e-11\n",
"Kurtosis: 4.886 Cond. No. 161.\n",
"==============================================================================\n",
"\n",
"Warnings:\n",
"[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
"\"\"\""
]
},
"execution_count": 33,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res.summary()"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array(['Sun', 'Sat', 'Thur', 'Fri'], dtype=object)"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data['day'].unique()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# $\\to$ Slide"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# scikit-learn"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.neural_network import MLPClassifier"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"clf = MLPClassifier()"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" perc_tip \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.059447 \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.160542 \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 3 \n",
" 0.166587 \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" Male \n",
" No \n",
" Sun \n",
" Dinner \n",
" 2 \n",
" 0.139780 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" Female \n",
" No \n",
" Sun \n",
" Dinner \n",
" 4 \n",
" 0.146808 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size perc_tip\n",
"0 16.99 1.01 Female No Sun Dinner 2 0.059447\n",
"1 10.34 1.66 Male No Sun Dinner 3 0.160542\n",
"2 21.01 3.50 Male No Sun Dinner 3 0.166587\n",
"3 23.68 3.31 Male No Sun Dinner 2 0.139780\n",
"4 24.59 3.61 Female No Sun Dinner 4 0.146808"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"data['sex'] = data['sex'] == 'Female'\n",
"data['smoker'] = data['smoker'] == 'Yes'\n",
"data['time'] = data['time'] == 'Dinner'"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" perc_tip \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" True \n",
" False \n",
" Sun \n",
" True \n",
" 2 \n",
" 0.059447 \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 3 \n",
" 0.160542 \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 3 \n",
" 0.166587 \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 2 \n",
" 0.139780 \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" True \n",
" False \n",
" Sun \n",
" True \n",
" 4 \n",
" 0.146808 \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size perc_tip\n",
"0 16.99 1.01 True False Sun True 2 0.059447\n",
"1 10.34 1.66 False False Sun True 3 0.160542\n",
"2 21.01 3.50 False False Sun True 3 0.166587\n",
"3 23.68 3.31 False False Sun True 2 0.139780\n",
"4 24.59 3.61 True False Sun True 4 0.146808"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 40,
"metadata": {},
"outputs": [],
"source": [
"data['good_tip'] = data['perc_tip'] > data['perc_tip'].mean()"
]
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {},
"outputs": [],
"source": [
"x = data.drop(['good_tip', 'day', 'perc_tip', 'tip'], axis=1)\n",
"y = data['good_tip']"
]
},
{
"cell_type": "code",
"execution_count": 44,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" \n",
" total_bill \n",
" tip \n",
" sex \n",
" smoker \n",
" day \n",
" time \n",
" size \n",
" perc_tip \n",
" good_tip \n",
" \n",
" \n",
" \n",
" \n",
" 0 \n",
" 16.99 \n",
" 1.01 \n",
" True \n",
" False \n",
" Sun \n",
" True \n",
" 2 \n",
" 0.059447 \n",
" False \n",
" \n",
" \n",
" 1 \n",
" 10.34 \n",
" 1.66 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 3 \n",
" 0.160542 \n",
" False \n",
" \n",
" \n",
" 2 \n",
" 21.01 \n",
" 3.50 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 3 \n",
" 0.166587 \n",
" True \n",
" \n",
" \n",
" 3 \n",
" 23.68 \n",
" 3.31 \n",
" False \n",
" False \n",
" Sun \n",
" True \n",
" 2 \n",
" 0.139780 \n",
" False \n",
" \n",
" \n",
" 4 \n",
" 24.59 \n",
" 3.61 \n",
" True \n",
" False \n",
" Sun \n",
" True \n",
" 4 \n",
" 0.146808 \n",
" False \n",
" \n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_bill tip sex smoker day time size perc_tip good_tip\n",
"0 16.99 1.01 True False Sun True 2 0.059447 False\n",
"1 10.34 1.66 False False Sun True 3 0.160542 False\n",
"2 21.01 3.50 False False Sun True 3 0.166587 True\n",
"3 23.68 3.31 False False Sun True 2 0.139780 False\n",
"4 24.59 3.61 True False Sun True 4 0.146808 False"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head()"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"res = clf.fit(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 47,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.5614754098360656"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# I'M CHEATING! I'M CHEATING!\n",
"res.score(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 48,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.tree import DecisionTreeClassifier, export_graphviz"
]
},
{
"cell_type": "code",
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"tree = DecisionTreeClassifier(max_depth=4)"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"res = tree.fit(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 51,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.6475409836065574"
]
},
"execution_count": 51,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res.score(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 52,
"metadata": {},
"outputs": [],
"source": [
"dot_data = export_graphviz(tree, out_file=None,\n",
" feature_names=x.columns,\n",
" filled=True, rounded=True,\n",
" special_characters=True)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"metadata": {},
"outputs": [],
"source": [
"import graphviz\n",
"graph = graphviz.Source(dot_data) "
]
},
{
"cell_type": "code",
"execution_count": 54,
"metadata": {},
"outputs": [
{
"data": {
"image/svg+xml": [
"\n",
"\n",
"\n",
"\n",
"\n",
"\n",
"Tree \n",
" \n",
"\n",
"0 \n",
" \n",
"total_bill ≤ 22.325 \n",
"gini = 0.4924 \n",
"samples = 244 \n",
"value = [137, 107] \n",
" \n",
"\n",
"1 \n",
" \n",
"total_bill ≤ 10.335 \n",
"gini = 0.4996 \n",
"samples = 169 \n",
"value = [82, 87] \n",
" \n",
"\n",
"0->1 \n",
" \n",
" \n",
"True \n",
" \n",
"\n",
"14 \n",
" \n",
"total_bill ≤ 48.3 \n",
"gini = 0.3911 \n",
"samples = 75 \n",
"value = [55, 20] \n",
" \n",
"\n",
"0->14 \n",
" \n",
" \n",
"False \n",
" \n",
"\n",
"2 \n",
" \n",
"smoker ≤ 0.5 \n",
"gini = 0.375 \n",
"samples = 24 \n",
"value = [6, 18] \n",
" \n",
"\n",
"1->2 \n",
" \n",
" \n",
" \n",
"\n",
"7 \n",
" \n",
"total_bill ≤ 20.47 \n",
"gini = 0.4988 \n",
"samples = 145 \n",
"value = [76, 69] \n",
" \n",
"\n",
"1->7 \n",
" \n",
" \n",
" \n",
"\n",
"3 \n",
" \n",
"time ≤ 0.5 \n",
"gini = 0.4567 \n",
"samples = 17 \n",
"value = [6, 11] \n",
" \n",
"\n",
"2->3 \n",
" \n",
" \n",
" \n",
"\n",
"6 \n",
" \n",
"gini = 0.0 \n",
"samples = 7 \n",
"value = [0, 7] \n",
" \n",
"\n",
"2->6 \n",
" \n",
" \n",
" \n",
"\n",
"4 \n",
" \n",
"gini = 0.2188 \n",
"samples = 8 \n",
"value = [1, 7] \n",
" \n",
"\n",
"3->4 \n",
" \n",
" \n",
" \n",
"\n",
"5 \n",
" \n",
"gini = 0.4938 \n",
"samples = 9 \n",
"value = [5, 4] \n",
" \n",
"\n",
"3->5 \n",
" \n",
" \n",
" \n",
"\n",
"8 \n",
" \n",
"total_bill ≤ 19.815 \n",
"gini = 0.4949 \n",
"samples = 129 \n",
"value = [71, 58] \n",
" \n",
"\n",
"7->8 \n",
" \n",
" \n",
" \n",
"\n",
"11 \n",
" \n",
"total_bill ≤ 20.67 \n",
"gini = 0.4297 \n",
"samples = 16 \n",
"value = [5, 11] \n",
" \n",
"\n",
"7->11 \n",
" \n",
" \n",
" \n",
"\n",
"9 \n",
" \n",
"gini = 0.4988 \n",
"samples = 122 \n",
"value = [64, 58] \n",
" \n",
"\n",
"8->9 \n",
" \n",
" \n",
" \n",
"\n",
"10 \n",
" \n",
"gini = 0.0 \n",
"samples = 7 \n",
"value = [7, 0] \n",
" \n",
"\n",
"8->10 \n",
" \n",
" \n",
" \n",
"\n",
"12 \n",
" \n",
"gini = 0.0 \n",
"samples = 3 \n",
"value = [0, 3] \n",
" \n",
"\n",
"11->12 \n",
" \n",
" \n",
" \n",
"\n",
"13 \n",
" \n",
"gini = 0.4734 \n",
"samples = 13 \n",
"value = [5, 8] \n",
" \n",
"\n",
"11->13 \n",
" \n",
" \n",
" \n",
"\n",
"15 \n",
" \n",
"total_bill ≤ 34.465 \n",
"gini = 0.3716 \n",
"samples = 73 \n",
"value = [55, 18] \n",
" \n",
"\n",
"14->15 \n",
" \n",
" \n",
" \n",
"\n",
"22 \n",
" \n",
"gini = 0.0 \n",
"samples = 2 \n",
"value = [0, 2] \n",
" \n",
"\n",
"14->22 \n",
" \n",
" \n",
" \n",
"\n",
"16 \n",
" \n",
"size ≤ 3.5 \n",
"gini = 0.4271 \n",
"samples = 55 \n",
"value = [38, 17] \n",
" \n",
"\n",
"15->16 \n",
" \n",
" \n",
" \n",
"\n",
"19 \n",
" \n",
"total_bill ≤ 39.075 \n",
"gini = 0.1049 \n",
"samples = 18 \n",
"value = [17, 1] \n",
" \n",
"\n",
"15->19 \n",
" \n",
" \n",
" \n",
"\n",
"17 \n",
" \n",
"gini = 0.3343 \n",
"samples = 33 \n",
"value = [26, 7] \n",
" \n",
"\n",
"16->17 \n",
" \n",
" \n",
" \n",
"\n",
"18 \n",
" \n",
"gini = 0.4959 \n",
"samples = 22 \n",
"value = [12, 10] \n",
" \n",
"\n",
"16->18 \n",
" \n",
" \n",
" \n",
"\n",
"20 \n",
" \n",
"gini = 0.0 \n",
"samples = 9 \n",
"value = [9, 0] \n",
" \n",
"\n",
"19->20 \n",
" \n",
" \n",
" \n",
"\n",
"21 \n",
" \n",
"gini = 0.1975 \n",
"samples = 9 \n",
"value = [8, 1] \n",
" \n",
"\n",
"19->21 \n",
" \n",
" \n",
" \n",
" \n",
" \n"
],
"text/plain": [
""
]
},
"execution_count": 54,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"graph"
]
},
{
"cell_type": "code",
"execution_count": 55,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.ensemble import RandomForestClassifier"
]
},
{
"cell_type": "code",
"execution_count": 56,
"metadata": {},
"outputs": [],
"source": [
"forest = RandomForestClassifier(max_depth=4)"
]
},
{
"cell_type": "code",
"execution_count": 57,
"metadata": {},
"outputs": [],
"source": [
"res = forest.fit(x, y)"
]
},
{
"cell_type": "code",
"execution_count": 58,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.6967213114754098"
]
},
"execution_count": 58,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"res.score(x, y)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}