2+2
log(1)

z = [1, 2, 3]
z

type(z)

z * 2

import numpy
numpy.log(1)

import numpy as np
np.log(1)

x = np.array(z)
x * 2

type(x)

np.tile(x,2)

x[1]

x[0:2]

y = x
x[2] = 10
x

y

x is y

x = np.arange(0,3)
x

y = np.copy(x)
x[2] = 10
x

y

a = 1
b = a
a = 2
b

def addone(a):
    a += 1
    return(a)

x = np.array([1, 2])
addone(x)

x


import scipy as sp
z = sp.randn(10)
z

from scipy import stats
stats.norm.cdf(1.645)

np.mean(z)

sp.mean(z)

z.mean()

import pandas as pd
gala = pd.read_table('http://people.bath.ac.uk/jjf23/data/gala.dat',index_col=0,delim_whitespace=True)
gala.head()

type(gala)

gala.describe().round(1)

gala.Species

gala['Species']

gala.iloc[0]

gala.iloc[-2:,0:3]

gala[gala.Species == gala.Endemics]

import seaborn.apionly as sns
iris = sns.load_dataset('iris')
iris.head()

iris.groupby('species').agg({'sepal_length': np.mean, 'sepal_width' : np.mean})

import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')

x = np.linspace(0, 2 * np.pi)
y = np.sin(x)
plt.plot(x, y)

plt.scatter(gala.Area, gala.Elevation)
plt.xlabel("Area")
plt.ylabel("Elevation")

import statsmodels.api as sm
x = gala.iloc[:,2:]
y = gala.Species
lmod = sm.OLS(y,sm.add_constant(x)).fit()
lmod.summary()

import statsmodels.formula.api as smf
lmod = smf.ols('Species ~ Area + Elevation + Nearest + Scruz + Adjacent', data=gala).fit()
lmod.summary()

lmod2 = smf.ols('Species ~ Area + Elevation + Nearest + Scruz + Adjacent + I(Area + Adjacent)', data=gala).fit()
lmod2.summary()

lmod.params

plt.scatter(lmod.fittedvalues, lmod.resid)
plt.axhline(0)

sm.qqplot(lmod.resid, line='r')