day_7_dhruvdhayal_ai_ml.py

# -*- coding: utf-8 -*-
"""Day-7_DHRUVDHAYAL_AI/ML.ipynb

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1npzLgzx3jal5ATGM0UjBN9wa1N6P346t

#Decision Tree Making!
"""

#Using the Decision Tree Concepts!
#Importing all theBuilt-In Libraries.
from sklearn import datasets;
from sklearn import svm, tree;
from sklearn import metrics;
from sklearn import model_selection;
import matplotlib.pyplot as plt;
import numpy as np;
import pandas as pd;

#Load the Values of the Datasets.
data=datasets.load_iris();

#Show the Values of the Data.
print("\n 1. Type of the Data Represented: ",type(data));
print("\n 2. Description of the Data complete: ",data);

#Now, we need to defined the load the data properly!
X=data.data;
y=data.target;
print("\n 1. Type of the Attributes: ",type(X));
print("\n 2. Total Length of the Attributes:  ",len(X));
print("\n 3. Type of the Labels: ",type(Y));
print("\n 4. Total Length of the Labels:  ",len(Y));

#Now, we need to split the values of the Data.

ratio=0.3;
Xtrain,Xtest,ytrain,ytest=model_selection.train_test_split(X,y,test_size=ratio,random_state=7);
print("\n 1. Training Data: ",Xtrain.shape," ",ytrain.shape);
print("\n 2, Testing Data: ",Xtest.shape," ",ytrain.shape);

#Now, we needto train the model in a proper Manner.
#Classification of the Model.

clff_model=tree.DecisionTreeClassifier(criterion='entropy',max_depth=None);

#Training the Model to become the Trained Data.
clff_model=clff_model.fit(Xtrain,ytrain);

#Now, we need to test the data based on it's labels.
#predict the training data for training accuracy.
ypredTrain=clff_model.predict(Xtrain);

#Predict the testing data for testing accuracy.
ypredTest=clff_model.predict(Xtest);

print("\n --> Predicted Training Data : ",ypredTrain.shape);
print("\n --> Predicted Testing Data : ",ypredTest.shape);

#Now, we need to calculate the values of the accuracy, precision, recall, f1-score.
#We, need to measure the Training and Testing Accuracy.

accTrain=metrics.accuracy_score(ypredTrain,ytrain);
accTest=metrics.accuracy_score(ypredTest,ytest);

print("\n --> Training Accuracy: ",accTrain);
print("\n --> Testing Accuracy: ",accTest);

#Now, we need to show the values of the Graph in decision forms.
import matplotlib.pyplot as plt;
plt.figure(1,figsize=(5,10));
tree.plot_tree(clff_model,filled=True);
plt.show();

"""# >> Now, we need to perform the decision tree to find the actual values on the Diabetes Datasets."""

#Importing all the built in Libraries in sklearn.
from sklearn import datasets;
from sklearn import svm;
from sklearn import metrics;
from sklearn import model_selection;

#Importing the another Libraries.
import matplotlib.pyplot as plt;
#import matplotlib.image as plt;
import pandas as pd;
import numpy as np;

#Now, we need to show the actual Values.
path='/content/diabetes.csv';
data=pd.read_csv(path);

#Showing the Values of the Data.
print("\n 1. Type of the Information Available in the Datasets of Diabetes: ",type(data));
print("\n 2. Complete Description of the Data Given Here: ",data.shape);
print("\n------------------------------------------------------------------------------------");
print("\n 3. Show the Data with Descriptions: \n\n",data);

#Now, we need to specify the data with a particular Locations.
x=data.drop('Outcome',axis=1,inplace=False);
y=data['Outcome'];

#Now, we need to split the data in training and testing.
ratio=0.3;
Xtrain,Xtest,ytrain,ytest=model_selection.train_test_split(x,y,test_size=ratio,random_state=7); # Change X to x
print("\n 1. Training Data Values: ",Xtrain.shape," ",ytrain.shape);
print("\n 2. Testing Data Values: ",Xtest.shape," ",ytest.shape);

#Now, we need to classify the Model.
#Proper Classification should be done on time!

clff_model=tree.DecisionTreeClassifier(criterion='entropy',max_depth=5);

#Training the Values of the Models.
clff_model=clff_model.fit(Xtrain,ytrain);

#Predict the values of the Training Data Values.
ypredTrain=clff_model.predict(Xtrain);

#Predict the Values of the Testing Data Values.
ypredTest=clff_model.predict(Xtest);

print("\n --> Traning Data Prediction: ",ypredTrain.shape);
print("\n --> Testing Data Prediction: ",ypredTest.shape);

#Now, we need to calculate the overall accuracy of the Model in  testing and training seperately!

accTrain=metrics.accuracy_score(ypredTrain,ytrain);
accTest=metrics.accuracy_score(ypredTest,ytest);

#Printing all overall values.
print("\n --> Training Accuracy: ",accTrain);
print("\n --> Testing Accuracy: ",accTest);

#Now, we need to show the values of the Graph forms!
plt.figure(1);
tree.plot_tree(clff_model,filled=True);

"""#Now, we make the direct acess data from the Google Drive Directly!"""