Program 1:- write a program of Data preprocessing

1. Handling missing values

 isnull()
 notnull()
 dropna()
 fillna()
 replace()
 interpolate()

# importing pandas as pd
import pandas as pd

# importing numpy as np
import numpy as np

# dictionary of lists
dict = {'First Score':[100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score':[np.nan, 40, 80, 98]}

# creating a dataframe from list

df = pd.DataFrame(dict)

# using isnull() function

df.isnull()

# importing pandas package

import pandas as pd

# making data frame from csv file

data = pd.read_csv("employees.csv")
# creating bool series True for NaN values
bool_series = pd.isnull(data["Gender"])

# filtering data
# displaying data only with Gender = NaN
data[bool_series]
# importing pandas as pd
import pandas as pd

# importing numpy as np
import numpy as np

# dictionary of lists
dict = {'First Score':[100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score':[np.nan, 40, 80, 98]}

# creating a dataframe using dictionary

df = pd.DataFrame(dict)

# using notnull() function

df.notnull()
# importing pandas package
import pandas as pd

# making data frame from csv file

data = pd.read_csv("employees.csv")

# creating bool series True for NaN values

bool_series = pd.notnull(data["Gender"])
# filtering data
# displaying data only with Gender = Not NaN
data[bool_series]

# importing pandas as pd
import pandas as pd

# importing numpy as np
import numpy as np

# dictionary of lists
dict = {'First Score':[100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score':[np.nan, 40, 80, 98]}

# creating a dataframe from dictionary

df = pd.DataFrame(dict)

# filling missing value using fillna()

df.fillna(0)
# importing pandas as pd

import pandas as pd

# importing numpy as np
import numpy as np

# dictionary of lists
dict = {'First Score':[100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score':[np.nan, 40, 80, 98]}
# creating a dataframe from dictionary
df = pd.DataFrame(dict)

# filling a missing value with

# previous ones
df.fillna(method ='pad')
# importing pandas as pd
import pandas as pd

# importing numpy as np
import numpy as np

# dictionary of lists
dict = {'First Score':[100, 90, np.nan, 95],
'Second Score': [30, 45, 56, np.nan],
'Third Score':[np.nan, 40, 80, 98]}

# creating a dataframe from dictionary

df = pd.DataFrame(dict)

# filling null value using fillna() function

df.fillna(method ='bfill')
Program 2: Write a python program to demonstrate various data visualisation
# importing pandas package
import pandas as pd

# making data frame from csv file

data = pd.read_csv("employees.csv")
# Printing the first 10 to 24 rows of
# the data frame for visualization
data[10:25]

# importing pandas package

import pandas as pd
# making data frame from csv file
data = pd.read_csv("employees.csv")

# Printing the first 10 to 24 rows of

# the data frame for visualization
data[10:25]

# importing pandas package

import pandas as pd

# making data frame from csv file

data = pd.read_csv("employees.csv")

# will replace Nan value in dataframe with value -99

data.replace(to_replace = np.nan, value = -99)

# importing pandas as pd
import pandas as pd

# Creating the dataframe

 df = pd.DataFrame({"A":[12, 4, 5, None, 1],
"B":[None, 2, 54, 3, None],
"C":[20, 16, None, 3, 8],
"D":[14, 3, None, None, 6]})

# Print the dataframe

Df

# importing the required module

import matplotlib.pyplot as plt

# x axis values
x = [1,2,3]
# corresponding y axis values
y = [2,4,1]

# plotting the points

plt.plot(x, y)

# naming the x axis

plt.xlabel('x - axis')
# naming the y axis
plt.ylabel('y - axis')

# giving a title to my graph

plt.title('My first graph!')

# function to show the plot

plt.show()
return probabilities

def predict(info, test):

probabilities = calculateClassProbabilities(info, test)
bestLabel, bestProb = None, -1
for classValue, probability in probabilities.items():
if bestLabel is None or probability > bestProb:
bestProb = probability
bestLabel = classValue
return bestLabel

def getPredictions(info, test):

predictions = []
for i in range(len(test)):
result = predict(info, test[i])
predictions.append(result)
return predictions

def accuracy_rate(test, predictions):

correct = 0
for i in range(len(test)):
if test[i][-1] == predictions[i]:
correct += 1
return (correct / float(len(test))) * 100.0

filename = r'E:\user\MACHINE LEARNING\machine learning algos\Naive bayes\filedata.csv'

mydata = csv.reader(open(filename, "rt"))
mydata = list(mydata)
mydata = encode_class(mydata)
for i in range(len(mydata)):
mydata[i] = [float(x) for x in mydata[i]]
ratio = 0.7
train_data, test_data = splitting(mydata, ratio)
print('Total number of examples are: ', len(mydata))
print('Out of these, training examples are: ', len(train_data))
print("Test examples are: ", len(test_data))
info = MeanAndStdDevForClass(train_data)
predictions = getPredictions(info, test_data)
accuracy = accuracy_rate(test_data, predictions)
print("Accuracy of your model is: ", accuracy)
1. Implementation of SVM Classification

# importing scikit learn with make_blobs

from sklearn.datasets.samples_generator import make_blobs
# creating datasets X containing n_samples
# Y containing two classes
X, Y = make_blobs(n_samples=500, centers=2,random_state=0, cluster_std=0.40)
import matplotlib.pyplot as plt
# plotting scatters
plt.scatter(X[:, 0], X[:, 1], c=Y, s=50, cmap='spring');
plt.show()
# creating linspace between -1 to 3.5
xfit = np.linspace(-1, 3.5)
# plotting scatter
plt.scatter(X[:, 0], X[:, 1], c=Y, s=50, cmap='spring')
# plot a line between the different sets of data
for m, b, d in [(1, 0.65, 0.33), (0.5, 1.6, 0.55), (-0.2, 2.9, 0.2)]:
yfit = m * xfit + b
plt.plot(xfit, yfit, '-k')
plt.fill_between(xfit, yfit - d, yfit + d, edgecolor='none',
color='#AAAAAA', alpha=0.4)
plt.xlim(-1, 3.5);
plt.show()
# importing required libraries

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
x = pd.read_csv("C:\...\cancer.csv")
a = np.array(x)
y = a[:,30] # classes having 0 and 1
x = np.column_stack((x.malignant,x.benign))
x.shape
print (x),(y)
program 3: Supervised Learning
1. Implementation of Linear Regression

import numpy as np
import matplotlib.pyplot as plt
def estimate_coef(x, y):
n = np.size(x)
m_x = np.mean(x)
m_y = np.mean(y)
SS_xy = np.sum(y*x) - n*m_y*m_x
SS_xx = np.sum(x*x) - n*m_x*m_x
b_1 = SS_xy / SS_xx
b_0 = m_y - b_1*m_x
return (b_0, b_1)
def plot_regression_line(x, y, b):
# plotting the actual points as scatter plot
plt.scatter(x, y, color = "m",marker = "o", s = 30)
y_pred = b[0] + b[1]*x
plt.plot(x, y_pred, color = "g")
plt.xlabel('x')
plt.ylabel('y')
plt.show()
def main():
x = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
y = np.array([1, 3, 2, 5, 7, 8, 8, 9, 10, 12])
b = estimate_coef(x, y)
print("Estimated coefficients:\nb_0 = {}\\nb_1 = {}".format(b[0], b[1]))
plot_regression_line(x, y, b)
if name == " main ":
 program 4 : Implementation of Logistic regression

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
import warnings
warnings.filterwarnings( "ignore" )
class LogitRegression() :
def init ( self, learning_rate, iterations ) :
self.learning_rate = learning_rate
self.iterations = iterations
def fit( self, X, Y ) :
self.m, self.n = X.shape
self.W = np.zeros( self.n )
self.b = 0
self.X = X
self.Y = Y
for i in range( self.iterations ) :
self.update_weights()
return self
def update_weights( self ) :
A = 1 / ( 1 + np.exp( - ( self.X.dot( self.W ) + self.b ) ) )
tmp = ( A - self.Y.T )
tmp = np.reshape( tmp, self.m )
dW = np.dot( self.X.T, tmp ) / self.m
db = np.sum( tmp ) / self.m
self.W = self.W - self.learning_rate * dW
self.b = self.b - self.learning_rate * db
return self
def predict( self, X ) :
Z = 1 / ( 1 + np.exp( - ( X.dot( self.W ) + self.b ) ) )
 Y = np.where( Z > 0.5, 1, 0 )

return Y
def main() :
df = pd.read_csv( "diabetes.csv" )
X = df.iloc[:,:-1].values
Y = df.iloc[:,-1:].values
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size = 1/3, random_state = 0 )
model = LogitRegression( learning_rate = 0.01, iterations = 1000 )
model.fit( X_train, Y_train )
model1 = LogisticRegression()
model1.fit( X_train, Y_train)
Y_pred = model.predict( X_test )
Y_pred1 = model1.predict( X_test )
correctly_classified = 0
correctly_classified1 = 0
count = 0
for count in range( np.size( Y_pred ) ) :
if Y_test[count] == Y_pred[count] :
correctly_classified = correctly_classified + 1
if Y_test[count] == Y_pred1[count] :
correctly_classified1 = correctly_classified1 + 1
count = count + 1
print( "Accuracy on test set by our model : ", (
correctly_classified / count ) * 100 )
print( "Accuracy on test set by sklearn model : ", (
correctly_classified1 / count ) * 100 )
if name == " main " :
main()
# importing pandas package
import pandas as pd
# making data frame from csv file
data = pd.read_csv("employees.csv")
# Printing the first 10 to 24 rows of
# the data frame for visualization
data[10:25]
Program 5:-. Implementation of Decision tree
classification import numpy as np
import pandas as pd
from sklearn.metrics import confusion_matrix
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
def importdata():
balance_data = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-
'+'databases/balance-scale/balance-scale.data',sep= ',', header = None)
print ("Dataset Length: ", len(balance_data))
print ("Dataset Shape: ", balance_data.shape)
print ("Dataset: ",balance_data.head())
return balance_data
def splitdataset(balance_data):
X = balance_data.values[:, 1:5]
Y = balance_data.values[:, 0]
X_train, X_test, y_train, y_test = train_test_split(
X, Y, test_size = 0.3, random_state = 100)
return X, Y, X_train, X_test, y_train, y_test
def train_using_gini(X_train, X_test, y_train):
clf_gini = DecisionTreeClassifier(criterion = "gini",random_state = 100,max_depth=3,
min_samples_leaf=5)
clf_gini.fit(X_train, y_train)
return clf_gini
def tarin_using_entropy(X_train, X_test, y_train):
clf_entropy = DecisionTreeClassifier(criterion = "entropy", random_state = 100,max_depth = 3,
min_samples_leaf = 5)
clf_entropy.fit(X_train, y_train)
 return clf_entropy
def prediction(X_test, clf_object):
y_pred = clf_object.predict(X_test)
print("Predicted values:")
print(y_pred)
return y_pred
def cal_accuracy(y_test, y_pred):
print("Confusion Matrix: ",confusion_matrix(y_test, y_pred))print ("Accuracy :
",accuracy_score(y_test,y_pred)*100)
print("Report : ",
classification_report(y_test, y_pred))
def main():
data = importdata()
X, Y, X_train, X_test, y_train, y_test = splitdataset(data)
clf_gini = train_using_gini(X_train, X_test, y_train)
clf_entropy = tarin_using_entropy(X_train, X_test, y_train)
print("Results Using Gini Index:")
y_pred_gini = prediction(X_test, clf_gini)
cal_accuracy(y_test, y_pred_gini)
print("Results Using Entropy:")
y_pred_entropy = prediction(X_test, clf_entropy)
cal_accuracy(y_test, y_pred_entropy)
if name ==" main ":
main()
Program 6:- Implementation of K-nearest Neighbor
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_iris

import numpy as np
import matplotlib.pyplot as plt

y = irisData.target
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state=42)
neighbors = np.arange(1, 9)
train_accuracy = np.empty(len(neighbors))
test_accuracy = np.empty(len(neighbors))
for i, k in enumerate(neighbors):
knn = KNeighborsClassifier(n_neighbors=k)
knn.fit(X_train, y_train)
train_accuracy[i] = knn.score(X_train, y_train)
test_accuracy[i] = knn.score(X_test, y_test)
plt.plot(neighbors, test_accuracy, label = 'Testing dataset Accuracy')
plt.plot(neighbors, train_accuracy, label = 'Training dataset Accuracy')
plt.legend()
plt.xlabel('n_neighbors')
plt.ylabel('Accuracy')
plt.show()
 Program 7:-Implementation of Naïve Bayes classifier algorithm

import math
import random
import csv
def encode_class(mydata):
classes = []
for i in range(len(mydata)):
if mydata[i][-1] not in classes:
classes.append(mydata[i][-1])
for i in range(len(classes)):
for j in range(len(mydata)):
if mydata[j][-1] == classes[i]:
mydata[j][-1] = i
return mydata
def splitting(mydata, ratio):
train_num = int(len(mydata) * ratio)
train = []
test = list(mydata)
while len(train) < train_num:
index = random.randrange(len(test))
train.append(test.pop(index))
return train, test
def groupUnderClass(mydata):
dict = {}
for i in range(len(mydata)):
if (mydata[i][-1] not in dict):
dict[mydata[i][-1]] = []
dict[mydata[i][-1]].append(mydata[i])
return dict
 return sum(numbers) / float(len(numbers))

def std_dev(numbers):
avg = mean(numbers)
variance = sum([pow(x - avg, 2) for x in numbers]) / float(len(numbers) - 1)
return math.sqrt(variance)

def MeanAndStdDev(mydata):
info = [(mean(attribute), std_dev(attribute)) for attribute in zip(*mydata)]
del info[-1]
return info

def MeanAndStdDevForClass(mydata):
info = {}
dict = groupUnderClass(mydata)
for classValue, instances in dict.items():
info[classValue] = MeanAndStdDev(instances)
return info

def calculateGaussianProbability(x, mean, stdev):

expo = math.exp(-(math.pow(x - mean, 2) / (2 * math.pow(stdev, 2))))
return (1 / (math.sqrt(2 * math.pi) * stdev)) * expo
def calculateClassProbabilities(info, test):
probabilities = {}

for classValue, classSummaries in info.items():

probabilities[classValue] = 1
for i in range(len(classSummaries)):
mean, std_dev = classSummaries[i]
x = test[i]
probabilities[classValue] *= calculateGaussianProbability(x, mean, std_dev)
Program8:- Build Artificial Neural Network model with back propagation
Let’s first understand the term neural networks. In a neural network, where neurons are
fed inputs which then neurons consider the weighted sum over them and pass it by an
activation function and passes out the output to next neuron.

Python: To run our script

Pip: Necessary to install Python
packages pip install tensorflow
pip install keras
# Importing libraries
from keras.datasets import imdb
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import
MaxPooling1D from keras.layers.embeddings import
Embedding
from keras.preprocessing import sequence# Our dictionary will
contain only of the top 7000 words appearing most frequently
top_words = 7000# Now we split our data-set into training and test data
(X_train, y_train), (X_test, y_test) =
imdb.load_data(num_words=top_words)# Looking at the nature of training
data
print(X_train[0])
print(y_train[0])print('Shape of training data: ')
print(X_train.shape)
print(y_train.shape)print('Shape of test data: ')
print(X_test.shape)
print(y_test.shape)
Output :
[1, 14, 22, 16, 43, 530, 973, 1622, 1385, 65, 458, 4468, 66, 3941, 4, 173, 36,
256, 5, 25, 100, 43, 838, 112, 50, 670, 2, 9, 35, 480, 284, 5, 150, 4, 172,
112, 167, 2, 336, 385, 39, 4, 172, 4536, 1111, 17, 546, 38, 13, 447, 4, 192,
50, 16, 6, 147, 2025, 19, 14, 22, 4, 1920, 4613, 469, 4, 22, 71, 87, 12, 16,
43, 530, 38, 76, 15, 13, 1247, 4, 22, 17, 515, 17, 12, 16, 626, 18, 2, 5, 62,
386, 12, 8, 316, 8, 106, 5, 4, 2223, 5244, 16, 480, 66, 3785, 33, 4, 130, 12,
16, 38, 619, 5, 25, 124, 51, 36, 135, 48, 25, 1415, 33, 6, 22, 12, 215, 28,
77, 52, 5, 14, 407, 16, 82, 2, 8, 4, 107, 117, 5952, 15, 256, 4, 2, 7, 3766,
5, 723, 36, 71, 43, 530, 476, 26, 400, 317, 46, 7, 4, 2, 1029, 13, 104, 88, 4,
381, 15, 297, 98, 32, 2071, 56, 26, 141, 6, 194, 2, 18, 4, 226, 22, 21, 134,
476, 26, 480, 5, 144, 30, 5535, 18, 51, 36, 28, 224, 92, 25, 104, 4, 226, 65,
16, 38, 1334, 88, 12, 16, 283, 5, 16, 4472, 113, 103, 32, 15, 16, 5345, 19,
178, 32]
1
Shape of training data:
(25000,)
(25000,)
Shape of test data:
(25000,)
(25000,)

# Padding the data samples to a maximum review length in

words max_words = 450X_train =
sequence.pad_sequences(X_train, maxlen=max_words)
X_test = sequence.pad_sequences(X_test, maxlen=max_words)# Building the
CNN Model
model = Sequential() # initilaizing the Sequential nature for CNN
model# Adding the embedding layer which will take in maximum of
450
words as input and provide a 32 dimensional output of those words which
belong in the top_words dictionary
model.add(Embedding(top_words, 32,
input_length=max_words)) model.add(Conv1D(32, 3,
padding='same', activation='relu')) model.add(MaxPooling1D())
model.add(Flatten())
model.add(Dense(250, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

model.compile(loss='binary_crossentropy', optimizer='adam',
metrics=['accuracy'])
model.summary()
Program 9:Implementing K-means
def ReadData(fileName):

# Read the file, splitting by lines

f = open(fileName, 'r');
lines = f.read().splitlines();
f.close();
items = [];
for i in range(1, len(lines)):
line = lines[i].split(',');
itemFeatures = [];
for j in range(len(line)-1):
# Convert feature value to float
v = float(line[j]);
# Add feature value to dict
itemFeatures.append(v);
items.append(itemFeatures);
shuffle(items);
return items;

def FindColMinMax(items):n
= len(items[0]);
minima = [sys.maxint for i in range(n)];
maxima = [-sys.maxint -1 for i in range(n)];
for item in items:
for f in range(len(item)):
if (item[f] < minima[f]):
minima[f] = item[f];
if (item[f] > maxima[f]):
maxima[f] = item[f];
return minima,maxima;
def InitializeMeans(items, k, cMin, cMax):
# Initialize means to random numbers between
# the min and max of each column/feature
f = len(items[0]); # number of features
means = [[0 for i in range(f)] for j in range(k)];
for mean in means:
for i in range(len(mean)):
# Set value to a random float
# (adding +-1 to avoid a wide placement of a mean)
mean[i] = uniform(cMin[i]+1, cMax[i]-1);
return means;

def EuclideanDistance(x, y):

S = 0; # The sum of the squared differences of the elements
for i in range(len(x)):
S += math.pow(x[i]-y[i], 2)
#The square root of the sum
return math.sqrt(S)

def UpdateMean(n,mean,item):
for i in range(len(mean)):
m = mean[i];
m = (m*(n-1)+item[i])/float(n);
mean[i] = round(m, 3);
return mean;

def Classify(means,item):
# Classify item to the mean with minimum distance
minimum = sys.maxint;
index = -1;
for i in range(len(means)):
# Find distance from item to mean
 dis = EuclideanDistance(item, means[i]);
if (dis < minimum):
minimum = dis;
index = i;
return index;

def CalculateMeans(k,items,maxIterations=100000):
# Find the minima and maxima for columns
cMin, cMax = FindColMinMax(items);
# Initialize means at random points
means = InitializeMeans(items,k,cMin,cMax);
# Initialize clusters, the array to hold
# the number of items in a class
clusterSizes= [0 for i in range(len(means))];
# An array to hold the cluster an item is in
belongsTo = [0 for i in range(len(items))];
# Calculate means
for e in range(maxIterations):
# If no change of cluster occurs, halt
noChange = True;
for i in range(len(items)):
item = items[i];
# Classify item into a cluster and update the
# corresponding means.
index = Classify(means,item);
clusterSizes[index] += 1;
cSize = clusterSizes[index];
means[index] = UpdateMean(cSize,means[index],item);
# Item changed cluster
if(index != belongsTo[i]):
noChange = False;
belongsTo[i] = index;
 # Nothing changed, return
if (noChange):
break;
return means;

def FindClusters(means,items):
clusters = [[] for i in range(len(means))]; # Init clusters
for item in items:
# Classify item into a cluster
index = Classify(means,item);
# Add item to cluster
clusters[index].append(item);
return clusters;