Scribd
Upload
12 views3 pages

Z-Test ND F-Test - Colab

Uploaded by

Subham Padhan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views3 pages

Z-Test ND F-Test - Colab

Uploaded by

Subham Padhan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

5/24/24, 11:29 AM z-test nd f-test - Colab

#Program to implement Z-test


#importing the library
from statsmodels.stats.weightstats import ztest as ztest
#create datasets
data1=[82,84,84,84,84,86,89,89,91,91,91,92,94,95,95,95,97,98,98,99,99,101,101,101,101,105,109,109,109,110,114]
data2=[90,90,91,91,91,92,93,93,96,96,96,96,96,96,96,97,99,99,103,103,104,104,104,104,105,107,112,112,112,113,115]
#perform z-test
ztest (data1,data2,value=0)

(-1.8480845559593855, 0.06459011160967605)

#Program to implement T-test


import scipy.stats as stats
#create datasets
group1=[14,15,15,16,13,8,17,16,8,10,12,9]
group2=[15,14,14,13,17,17,10,12,12,9,11,11,14]
#perform t-test
stats.ttest_ind(a=group1 , b=group2 ,equal_var=True)

TtestResult(statistic=-0.21600462355982053, pvalue=0.8308883644471101, df=23.0)

#Program to implement F-test


#import nececssary libraries
import numpy as np
import scipy.stats
#create datasets
data1=[23,24,16,16,27,28]
data2=[16,17,17,19,22,21]
#convert the list into array
x=np.array(data1)
y=np.array(data2)
#calculate variance of each dataset
print(np.var(data1),np.var(data2))
#define f-test function
def f_test(x,y):
f=np.var(data1,ddof=1)/np.var(data2 , ddof=1) #f-test formula
dfn=x.size-1 #degree of freedom numerator
dfd=y.size-1 #degree of freedom denominator
p=1-scipy.stats.f.cdf(f,dfn,dfd)
return f,p
f_test(x,y)

22.888888888888886 4.888888888888889
(4.681818181818181, 0.05775084108450956)

#Implementing of One-way ANNOVA


from scipy.stats import f_oneway
Sample1=[89,89,88,78,79]
Sample2=[93,92,94,89,88]
Sample3=[89,88,89,93,90]
Sample4=[81,78,81,92,82]
f_oneway(Sample1,Sample2,Sample3,Sample4)

F_onewayResult(statistic=4.625000000000002, pvalue=0.016336459839780215)

#Implementation of TWO-way ANNOVA


import statsmodels.api as sm
from statsmodels.formula.api import ols
import pandas as pd
import numpy as np

dataframe=pd.DataFrame({
'Fertiliser': np.repeat(['daily','weekly'],15),
'Watering': np.repeat(['daily','weekly'],15),
'height': [14,16,15,15,16,13,12,11,14,15,16,16,17,18,14,13,14,14,14,15,16,16,12,11,14,15,16,16,17,18]
})
model = ols('height ~ C(Fertiliser)+C(Watering)+C(Fertiliser):C(Watering)',data=dataframe).fit()
result = sm.stats.anova_lm(model ,typ=2)
print(result)

sum_sq df F PR(>F)
C(Fertiliser) 2.732467e-13 1.0 7.860521e-14 1.000000
C(Watering) 2.715774e-02 1.0 7.812500e-03 0.930197
C(Fertiliser):C(Watering) 3.333333e-02 1.0 9.589041e-03 0.922691
Residual 9.733333e+01 28.0 NaN NaN

https://colab.research.google.com/drive/16BJz9lXMr49NGNOf9rCfT2vsNQsTWT6S#scrollTo=6qN56iIvK23a&printMode=true 1/3
5/24/24, 11:29 AM z-test nd f-test - Colab

# KNN REGRESSION
from sklearn.neighbors import KNeighborsRegressor
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# GENERATE SOME EXAMPLES DATA


X, y = make_regression(n_samples=100, n_features=10, noise=0.5 ,random_state=42)

# SPLIT THE DATA INTO TRAINING AND TESTING SETS


X_train, X_test, y_train ,y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# CREATE AND FIT THE KNN REGRESSION MODEL


k = 5 # NUMBER OF NEIGHBORS
knn = KNeighborsRegressor (n_neighbors=k)
knn.fit (X_train, y_train)

# PREDICT ON THE TESTING SET


y_pred = knn.predict (X_test)

# CALCULATE MEAN SQUARED ERROR


mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

Mean Squared Error: 23626.918831420033

# RIDGE_LASSO_REGRESSION
from sklearn.linear_model import Ridge
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# GENERATE SOME EXAMPLES DATA


X, y = make_regression(n_samples=100, n_features=10, noise=0.5 ,random_state=42)

# SPLIT THE DATA INTO TRAINING AND TESTING SETS


X_train, X_test, y_train ,y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# CREATE AND FIT THE RIDGE REGRESSION MODEL


ridge = Ridge(alpha=1.0) # YOU CAN ADJUST THE REGULARIZATION STRENGHT WITH THW ALPHA PARAMETER
ridge.fit (X_train, y_train)

# PREDICT ON THE TESTING SET


y_pred = ridge.predict (X_test)

# CALCULATE MEAN SQUARED ERROR


mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

Mean Squared Error: 12.652111318755058

# LASSO_REGRESSION
from sklearn.linear_model import Lasso
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# GENERATE SOME EXAMPLES DATA


X, y = make_regression(n_samples=100, n_features=10, noise=0.5 ,random_state=42)

# SPLIT THE DATA INTO TRAINING AND TESTING SETS


X_train, X_test, y_train ,y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# CREATE AND FIT THE LASSO REGRESSION MODEL


lasso = Lasso(alpha=1.0) # YOU CAN ADJUST THE REGULARIZATION STRENGHT WITH THW ALPHA PARAMETER
lasso.fit (X_train, y_train)

# PREDICT ON THE TESTING SET


y_pred = lasso.predict (X_test)

# CALCULATE MEAN SQUARED ERROR


mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

Mean Squared Error: 16.48819237719428

https://colab.research.google.com/drive/16BJz9lXMr49NGNOf9rCfT2vsNQsTWT6S#scrollTo=6qN56iIvK23a&printMode=true 2/3
5/24/24, 11:29 AM z-test nd f-test - Colab

https://colab.research.google.com/drive/16BJz9lXMr49NGNOf9rCfT2vsNQsTWT6S#scrollTo=6qN56iIvK23a&printMode=true 3/3

You might also like