Simple-Dataframe-For-Statsmodel

Sat 17 May 2025 
from __future__ import print_function
import statsmodels.api as sm
import pandas as pd
from patsy import dmatrices

df = sm.datasets.get_rdataset("Guerry", "HistData").data

df.head()
dept Region Department Crime_pers Crime_prop Literacy Donations Infants Suicides MainCity ... Crime_parents Infanticide Donation_clergy Lottery Desertion Instruction Prostitutes Distance Area Pop1831
0 1 E Ain 28870 15890 37 5098 33120 35039 2:Med ... 71 60 69 41 55 46 13 218.372 5762 346.03
1 2 N Aisne 26226 5521 51 8901 14572 12831 2:Med ... 4 82 36 38 82 24 327 65.945 7369 513.00
2 3 C Allier 26747 7925 13 10973 17044 114121 2:Med ... 46 42 76 66 16 85 34 161.927 7340 298.26
3 4 E Basses-Alpes 12935 7289 46 2733 23018 14238 1:Sm ... 70 12 37 80 32 29 2 351.399 6925 155.90
4 5 E Hautes-Alpes 17488 8174 69 6962 23076 16171 1:Sm ... 22 23 64 79 35 7 1 320.280 5549 129.10

5 rows × 23 columns

df.shape

(86, 23)

df.describe()
dept Crime_pers Crime_prop Literacy Donations Infants Suicides Wealth Commerce Clergy Crime_parents Infanticide Donation_clergy Lottery Desertion Instruction Prostitutes Distance Area Pop1831
count 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000
mean 46.883721 19754.406977 7843.058140 39.255814 7075.546512 19049.906977 36522.604651 43.500000 42.802326 43.430233 43.500000 43.511628 43.500000 43.500000 43.500000 43.127907 141.872093 207.953140 6146.988372 378.628721
std 30.426157 7504.703073 3051.352839 17.364051 5834.595216 8820.233546 31312.532649 24.969982 25.028370 24.999549 24.969982 24.948297 24.969982 24.969982 24.969982 24.799809 520.969318 109.320837 1398.246620 148.777230
min 1.000000 2199.000000 1368.000000 12.000000 1246.000000 2660.000000 3460.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 1.000000 0.000000 0.000000 762.000000 129.100000
25% 24.250000 14156.250000 5933.000000 25.000000 3446.750000 14299.750000 15463.000000 22.250000 21.250000 22.250000 22.250000 22.250000 22.250000 22.250000 22.250000 23.250000 6.000000 121.383000 5400.750000 283.005000
50% 45.500000 18748.500000 7595.000000 38.000000 5020.000000 17141.500000 26743.500000 43.500000 42.500000 43.500000 43.500000 43.500000 43.500000 43.500000 43.500000 41.500000 33.000000 200.616000 6070.500000 346.165000
75% 66.750000 25937.500000 9182.250000 51.750000 9446.750000 22682.250000 44057.500000 64.750000 63.750000 64.750000 64.750000 64.750000 64.750000 64.750000 64.750000 64.750000 113.750000 289.670500 6816.500000 444.407500
max 200.000000 37014.000000 20235.000000 74.000000 37015.000000 62486.000000 163241.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 86.000000 4744.000000 539.213000 10000.000000 989.940000

Score: 5

Category: statsmodel