Data Mining And Data Warehousing
Bayesian Classifier - Concept
if __name__ == "__main__":
# Each transaction as a set
transactions = [
{'milk', 'bread', 'butter','beer'},
{'beer', 'bread'},
{'milk', 'bread', 'beer', 'butter'},
{'bread', 'butter'}
]
# Example: check if 'milk' is in a transaction
print('milk' in transactions[0]) # True
# Example: subset check (important in Apriori)
itemset = {'beer', 'bread'}
print(itemset.issubset(transactions[2])) # True
count = 0
for i in transactions:
if itemset.issubset(i):
count += 1
print(itemset, ": ",count)
Close points to given points
import math
#from given point find nearest points.
if __name__ == "__main__":
given_point = (2, 3)
points = [
(1, 2),
(3, 4),
(5, 6),
(2.1, 3.2),
(10, 10)
]
radius = 1.5 # nearer if distance is <= radius.
close_points = [] #list of point closer to given_point (2,3)
close_points.append(given_point)
distances = []
for point in points: #Euclidean Distance formula
distance = math.sqrt((point[0] - given_point[0])**2 +
(point[1] - given_point[1])**2)
distances.append(distance)
if distance <= radius:
close_points.append(point)
print("Points closer to given point:", close_points)
print("Distances: ", distances)
x = []
y = []
for point in points:
x.append(point[0])
y.append(point[1])
print(f"x:{sum(x)/len(x)}, y: {sum(y)/len(y)}")
Data Preprocessing
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
if __name__ == "__main__":
data = {
'Age': [15, 16, None, 15,34,23,24,25,28,12,14,15],
'Gender': ['Male', 'Female', 'Female', 'Male','Female', 'Male','Female', 'Male','Female', 'Male','Female','Male'],
'Marks': [85, 90, 88, 85,45,56,67,78,98,12,23,45]
}
df = pd.DataFrame(data) #creating data frame
print(df) #printing data frame
mean_age = df['Age'].mean() # calculating mean of age
df.fillna({"Age":mean_age}, inplace=True) # assigning mean_age to empty age cell
print(df)
df = df.drop_duplicates() #
#tranforming male to 1 and female to 0
df['Gender'] = df['Gender'].map({'Male': 1, 'Female': 0})
print(df)
scaler = MinMaxScaler()
#transforming age in range 0 to 1 using MinMax Normalization
df[['Age', 'Marks']] = scaler.fit_transform(df[['Age', 'Marks']])
print(df)