Machine learning

import pandas
data = pandas.read_csv("https://modcom.co.ke/datasets/Customers.csv")
data

data.describe()

data

# this is a jupiter Note book
#there are teo typed 
# 1. classification - its when you predict  a categorical variable 
# EXAMPLE : yes / no , email is  spam/not spam /Primary.default /not default
# EXAMPLE :is it team A OR B,Fraud /not Fraud ,Bad /Good Nisan/toyota /BMW
 
 
# 2. Regression - its when you want to predict a continous variable 
# Example predict age weight hright bp temp speed profit , losses ,tax
# Example predict ,price , salary cost.points  score . loan amount ,sales 
 
 
# we will do classification
#  we will use an IRIS DATASET
 
import pandas
data = pandas.read_csv("https://modcom.co.ke/datasets/iris.csv")
data
 
# Objaective Train a computer about flowers , then use it to  predict flowers in future

# get basics statistics
data.describe()

# we need to train a machine learning model (ML) about flowers 
#  step 1 : Split data into Pridictors and Predicted
# Predictors :sepallength   sepalwidth  petallength petalwidth
# predicted :class
 
# Predicors are x , predicted is y
 
array = data.values
array
 
X= array[:,0:4] # :full colons means all rows , 0:3 means the first 4 columms
Y= array[:, 4 ]#; full colons means all rows ,4 means the fourth column

# step two : Split  split x  and y again
# x holds predictors  Predictors :sepallength   sepalwidth  petallength petalwidth
# Y holds predicted - class
# split to training  takes (70% of data ) and testing data  take (30 % of data )
 
from sklearn import model_selection
X_train,X_test,Y_train,Y_test = model_selection.train_test_split(X,Y,
                                                            test_size=0.3,
                                                            random_state=42)

# STEP 3 :train the models
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
 
#  pick one model
model =RandomForestClassifier()
model.fit(X_train, Y_train) # we train with 70% of data

#  step 4 : Test the model  accuracy
predictions =model.predict(X_test)
print('Model Predicted', predictions)
#  we have the Y_text containing the  the flowers classes 
print('EXPECTED', Y_test)
 
# get accuracy 
from sklearn.metrics import accuracy_score
score = accuracy_score(Y_test, predictions)
print('your score is ', score)
 
 
# the models scores 97% using Gausian

#  go get a flower from the farm ,take measurement of thr flower
 
flower=[[0.3 , 0.2, 0.9, 0.3]] 
#  whick flower is this ?
outcome = model.predict(flower)
print('your flower is likely to be' , outcome)
 
# we can trust the model since  it got a over 75% in testing