Ml lab manual

 

Pdf manual 👇👇

Code👇👇

1. The probability that it is Friday and that a student is absent is 3 %. Since there are 5 school days in a week, the probability that it is Friday is 20 %. What is the probability that a student is absent given that today is Friday?

probitisFridaynstudentAbsent=float(input("Enter the probability of being Friday and student is absent: ")) probitisFriday=0.2 pstudentisAbsentgivenitisFriday=probitisFridaynstudentAbsent/probitisFriday print("Probability that student is absent given it is Friday is:", pstudentisAbsentgivenitisFriday) """ OUTPUT: Enter the probability of being Friday and student is absent: 0.03 Probability that student is absent given it is Friday is: 0.15 """

2. Extract the data from database using python

#Import MySQL Connector for Python import mysql.connector #SET MYSQL CONNECTION mydb = mysql.connector.connect( host="localhost", user="root", password="Root123$" ) #CREATE CURSOR INSTANCE mycursor = mydb.cursor() print("Database connection successful ",mydb) #CREATE DATABASE mydatabase mycursor.execute("CREATE DATABASE IF NOT EXISTS mydatabase") #SHOW DATABASE mycursor.execute("SHOW DATABASES") for x in mycursor: print(x) #SET mydatabase connection mydb = mysql.connector.connect( host="localhost", user="root", password="Root123$", database="mydatabase" ) #CREATE CURSOR INSTANCE mycursor = mydb.cursor() print("Database connection successful ",mydb) #Change to mydatabase and CREATE TABLE customers with id, name and address fields mycursor.execute("use mydatabase") mycursor.execute("CREATE TABLE IF NOT EXISTS customers (id INT AUTO_INCREMENT PRIMARY KEY, name VARCHAR(255), address VARCHAR(255))") print("Created customers table") #SHOW TABLES in mydatabase mycursor.execute("SHOW TABLES") for x in mycursor: print(x) #INSERT MULTIPLE RECORDS into customer table sql = "INSERT INTO customers (name, address) VALUES (%s, %s)" val = [ ('Peter', 'Lowstreet 4'), ('Amy', 'Apple st 652'), ('Hannah', 'Mountain 21'), ('Michael', 'Valley 345'), ('Sandy', 'Ocean blvd 2'), ('Vicky', 'Yellow Garden 2'), ('Ben', 'Park Lane 38'), ('William', 'Central st 954'), ('Chuck', 'Main Road 989'), ('Viola', 'Sideway 1633') ] mycursor.executemany(sql, val) mydb.commit() print(mycursor.rowcount, "records were inserted.") #RETRIEVE DATA from customers table mycursor.execute("SELECT * FROM customers ") myresult = mycursor.fetchall() for x in myresult: print(x) #WHERE CLAUSE and LIKE WILDCARDS sql = "SELECT * FROM customers WHERE address LIKE '%way%'" mycursor.execute(sql) myresult = mycursor.fetchall() for x in myresult: print(x) #UPDATING RECORDS my_sql = "UPDATE customers SET address = 'Road N0 4, Gandhinagar' WHERE name= ‘Ben’ my_cursor.execute(my_sql) mydb.commit() #ORDERING RESULTS my_cursor.execute("SELECT * FROM customers ORDER BY name DESC") result = my_cursor.fetchall() for row in result: print(row) #DELETE RECORDS my_sql = "DELETE FROM customers WHERE name = 'Hannah'" my_cursor.execute(my_sql) mydb.commit() #DROP TABLE customers sql = "DROP TABLE customers" mycursor.execute(sql) mydb.commit() """ OUTPUT: Database connection successful <mysql.connector.connection_cext.CMySQLConnection object at 0x0000028AEDC3CAF0> ('information_schema',) ('mydatabase',) ('mysql',) ('performance_schema',) ('sakila',) ('sys',) ('world',) Database connection successful <mysql.connector.connection_cext.CMySQLConnection object at 0x0000028AEDC46640> Created customers table ('customers',) 10 records were inserted. (1, 'Peter', 'Lowstreet 4') (2, 'Amy', 'Apple st 652') (3, 'Hannah', 'Mountain 21') (4, 'Michael', 'Valley 345') (5, 'Sandy', 'Ocean blvd 2') (6, 'Vicky', 'Yellow Garden 2') (7, 'Ben', 'Park Lane 38') (8, 'William', 'Central st 954') (9, 'Chuck', 'Main Road 989') (10, 'Viola', 'Sideway 1633') (10, 'Viola', 'Sideway 1633') Displaying records in descending order (8, 'William', 'Central st 954') (10, 'Viola', 'Sideway 1633') (6, 'Vicky', 'Yellow Garden 2') (5, 'Sandy', 'Ocean blvd 2') (1, 'Peter', 'Lowstreet 4') (4, 'Michael', 'Valley 345') (3, 'Hannah', 'Mountain 21') (9, 'Chuck', 'Main Road 989') (7, 'Ben', 'Road N0 4, Gandhinagar') (2, 'Amy', 'Apple st 652') """

3. Implement k-nearest neighbours classification using python

#knn.py file # Import libraries import numpy as np from sklearn import datasets from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt from matplotlib.colors import ListedColormap def euclidean_distance(x1, x2): return np.sqrt(np.sum((x1 - x2)**2)) class KNN: def __init__(self, k=3): self.k = k def fit(self, X, y): self.X_train = X self.y_train = y def predict(self, X): y_pred = [self._predict(x) for x in X] return np.array(y_pred) def _predict(self, x): # Compute distances between x and all examples in the training set distances = [euclidean_distance(x, x_train) for x_train in self.X_train] # Sort by distance and return indices of the first k neighbors k_idx = np.argsort(distances)[:self.k] # Extract the labels of the k nearest neighbor training samples k_neighbor_labels = [self.y_train[i] for i in k_idx] # return the most common class label most_common = Counter(k_neighbor_labels).most_common(1) return most_common[0][0] #Expt3.py file import numpy as np from collections import Counter # import the KNN implementation from knn.py from knn import KNN cmap=ListedColormap(["#000FFF", "#FFF000","#00FF00"]) # Iris data has 50 samples for each different species of Iris flower(total of 150 examples). # For each sample we have 4 features sepal length, width and petal length and width and a iris species name(class/label). # Load iris dataset iris=datasets.load_iris() X,y=iris.data,iris.target # Viualize sepal length, sepal width data of iris data print( “Plot showing sepal length, sepal width data of iris data”) plt.figure() plt.scatter(X[:,0],X[:,1],c=y,cmap=cmap,edgecolor='none',s=40) plt.show() # split data into train and test set Xtrain, Xtest, Ytrain, Ytest= train_test_split(X,y,test_size=0.2, random_state=1234) clf=KNN(k=5) clf.fit(Xtrain,Ytrain) predictions=clf.predict(Xtest) acc=np.sum(predictions==Ytest)/len(Ytest) print("Accuracy of user defined KNN classifier for k=5 neighbors on iris dataset is: %0.3f "%acc) """ output Accuracy of user defined KNN classifier for k=5 neighbors on iris dataset is: 0.967 """

4. Given the following data, which specify classifications for nine combinations of VAR1 and VAR2 predict a classification for a case where VAR1=0.906 and VAR2=0.606, using the result of k-means clustering with 3 means (i.e., 3 centroids)

# Implementing K-means algorithm import numpy as np import pandas as pd import matplotlib.pyplot as plt from copy import deepcopy # Load data data = pd.read_csv('data.csv') f1 = data['A'].values f2 = data['B'].values X = np.array(list(zip(f1, f2))) plt.scatter(f1, f2, c='black', s=200) # Euclidean Distance Caculator def dist(a, b, ax=1): return np.linalg.norm(a - b, axis=ax) # Number of clusters k = 3 # initial cluster centroids C=data.values[0:k] C_x=C[0][0],C[1][0],C[2][0] C_y=C[0][1],C[1][1],C[2][1] print("Data points with initial centroids") plt.scatter(f1, f2, c='#050505', s=200) plt.scatter(C_x, C_y, marker='*', s=200, c='pink') # To store the value of centroids when it updates C_old = np.zeros(C.shape) # Cluster Lables(0, 1, 2) clusters = np.zeros(len(X)) # Error func. - Distance between new centroids and old centroids error = dist(C, C_old, None) # Loop will run till the error becomes zero while error != 0: # Assigning each value to its closest cluster for i in range(len(X)): distances = dist(X[i], C) cluster = np.argmin(distances) # returns index of minimum value clusters[i] = cluster # Storing the old centroid values C_old = deepcopy(C) # Finding the new centroids by taking the average value for i in range(k): points = [X[j] for j in range(len(X)) if clusters[j] == i] C[i] = np.mean(points, axis=0) error = dist(C, C_old, None) print("Colored data points in clusters with cluster centroids (*)") colors = ['r', 'g', 'b'] fig, ax = plt.subplots() for i in range(k): points = np.array([X[j] for j in range(len(X)) if clusters[j] == i]) ax.scatter(points[:, 0], points[:, 1], s=200, c=colors[i]) ax.scatter(C[:, 0], C[:, 1], marker='*', s=200, c='#050505') dist([0.906, 0.606],C) cluster = np.argmin(distances) print("Data point [0.906, 0.606] belongs to cluster",cluster) """ Data point [0.906, 0.606] belongs to cluster 2 """