└── TASK-01 IRIS FLOWER CLASSIFICATION


/TASK-01 IRIS FLOWER CLASSIFICATION:
--------------------------------------------------------------------------------
  1 | #Import Libraries/Packages
  2 | import pandas as pd
  3 | import numpy as np
  4 | import matplotlib.pyplot as plt
  5 | import seaborn as sns
  6 | %matplotlib inline
  7 | import warnings
  8 | warnings.filterwarnings('ignore')
  9 | import pandas as pd
 10 | 
 11 | # Load the csv file into a DataFrame
 12 | dataset = pd.read_csv("Iris.csv")
 13 | 
 14 | dataset
 15 | # Shape of Dataset
 16 | dataset.shape
 17 | #Display the first few rows of the DataFrame
 18 | dataset.head()
 19 | #Checking Null Values
 20 | dataset.isnull().sum()
 21 | #Dataset Summary
 22 | dataset.info()
 23 | #Dataset Statistical Summary
 24 | dataset.describe()
 25 | # To display no. of samples on each class.
 26 | dataset['Species'].value_counts()
 27 | dataset['Species'].value_counts().plot(kind = 'pie',  autopct = '%1.1f%%', shadow = True, explode = [0.05,0.05,0.05])
 28 | dataset.corr()
 29 | import seaborn as sns
 30 | import matplotlib.pyplot as plt
 31 | 
 32 | plt.figure(figsize=(9, 7))
 33 | sns.heatmap(dataset.corr(), cmap='CMRmap', annot=True, linewidths=2)
 34 | plt.title("Correlation Graph", size=20)
 35 | plt.show()
 36 | #Label encoding for categorical variables
 37 | from sklearn.preprocessing import LabelEncoder
 38 | le = LabelEncoder()
 39 | dataset['Species'] = le.fit_transform(dataset['Species'])
 40 | dataset.head()
 41 | dataset['Species'].unique()
 42 | import pandas as pd
 43 | from sklearn.model_selection import train_test_split
 44 | 
 45 | # Load the CSV file into a DataFrame
 46 | df = pd.read_csv("Iris.csv")
 47 | 
 48 | features = ['SepalLengthCm', 'SepalWidthCm', 'PetalLengthCm', 'PetalWidthCm']
 49 | X = df.loc[:, features].values
 50 | Y = df['Species'].values
 51 | 
 52 | # Split the dataset into training and test sets
 53 | X_Train, X_Test, Y_Train, Y_Test = train_test_split(X, Y, test_size=0.2, random_state=0)
 54 | 
 55 | print(X_Train.shape)
 56 | Y_Train.shape
 57 | X_Test.shape
 58 | Y_Test.shape
 59 | # Feature Scaling to bring all the variables in a single scale.
 60 | from sklearn.preprocessing import StandardScaler
 61 | sc = StandardScaler()
 62 | X_Train = sc.fit_transform(X_Train)
 63 | X_Test = sc.transform(X_Test)
 64 | 
 65 | 
 66 | # Importing some metrics for evaluating  models.
 67 | from sklearn import metrics
 68 | from sklearn.metrics import accuracy_score
 69 | from sklearn.metrics import  classification_report
 70 | from sklearn.metrics import confusion_matrix
 71 | from sklearn.linear_model import LogisticRegression
 72 | log_model= LogisticRegression(random_state = 0)
 73 | log_model.fit(X_Train, Y_Train)
 74 | 
 75 | # model training
 76 | log_model.fit(X_Train, Y_Train)
 77 | 
 78 | # Predicting
 79 | Y_Pred_Test_log_res=log_model.predict(X_Test)
 80 | 
 81 |      
 82 | 
 83 | print(Y_Pred_Test_log_res)
 84 | log_model = LogisticRegression(random_state=0, max_iter=100)
 85 | from sklearn import metrics
 86 | 
 87 | accuracy = metrics.accuracy_score(Y_Test, Y_Pred_Test_log_res)
 88 | print("Accuracy:", accuracy * 100)
 89 | from sklearn.metrics import  classification_report
 90 | print(classification_report(Y_Test, Y_Pred_Test_log_res))
 91 | from sklearn.metrics import confusion_matrix
 92 | confusion_matrix(Y_Test,Y_Pred_Test_log_res )
 93 | from sklearn.neighbors import KNeighborsClassifier
 94 | knn_model = KNeighborsClassifier(n_neighbors=3, weights='distance', algorithm='auto')
 95 | 
 96 | # Importing KNeighborsClassifier 
 97 | from sklearn.neighbors import KNeighborsClassifier
 98 | knn_model = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
 99 | 
100 | # model training
101 | knn_model.fit(X_Train, Y_Train)
102 | 
103 | # Predicting
104 | Y_Pred_Test_knn=knn_model.predict(X_Test)
105 |      
106 | 
107 | # model training
108 | log_model.fit(X_Train, Y_Train)
109 | Y_Pred_Test_knn
110 | print("Accuracy:",metrics.accuracy_score(Y_Test,Y_Pred_Test_knn)*100)
111 | print(classification_report(Y_Test,Y_Pred_Test_knn))
112 | confusion_matrix(Y_Test, Y_Pred_Test_knn)
113 | from sklearn.tree import DecisionTreeClassifier
114 | dec_tree = DecisionTreeClassifier(criterion='entropy',splitter='best',max_depth=6)
115 | 
116 | # model training
117 | dec_tree.fit(X_Train, Y_Train)
118 | 
119 | # Predicting
120 | Y_Pred_Test_dtr=dec_tree.predict(X_Test)
121 |      
122 | 
123 | Y_Pred_Test_dtr
124 | print("Accuracy:",metrics.accuracy_score(Y_Test, Y_Pred_Test_dtr)*100)
125 | 
126 | print(classification_report(Y_Test, Y_Pred_Test_dtr))
127 | confusion_matrix(Y_Test, Y_Pred_Test_dtr)
128 | from sklearn.naive_bayes import GaussianNB
129 | nav_byes = GaussianNB()
130 | 
131 | # model training
132 | nav_byes.fit(X_Train, Y_Train)
133 | 
134 | # Predicting
135 | Y_Pred_Test_nvb=nav_byes.predict(X_Test)
136 |      
137 | 
138 | Y_Pred_Test_nvb
139 | print("Accuracy:",metrics.accuracy_score(Y_Test, Y_Pred_Test_nvb)*100)
140 | 
141 | 
142 | print(classification_report(Y_Test, Y_Pred_Test_nvb))
143 | confusion_matrix(Y_Test,Y_Pred_Test_nvb )
144 | from sklearn.svm import SVC
145 | svm_model=SVC(C=500, kernel='rbf')
146 | 
147 | # model training
148 | svm_model.fit(X_Train, Y_Train)
149 | 
150 | # Predicting
151 | Y_Pred_Test_svm=svm_model.predict(X_Test)
152 |      
153 | 
154 | Y_Pred_Test_svm
155 | print("Accuracy:",metrics.accuracy_score(Y_Test,Y_Pred_Test_svm)*100)
156 | onfusion_matrix(Y_Test,Y_Pred_Test_svm )
157 | print("Accuracy of Logistic Regression Model:",metrics.accuracy_score(Y_Test, Y_Pred_Test_log_res)*100)
158 | print("Accuracy of KNN Model:",metrics.accuracy_score(Y_Test,Y_Pred_Test_knn)*100)
159 | print("Accuracy of Decision Tree Model:",metrics.accuracy_score(Y_Test, Y_Pred_Test_dtr)*100)
160 | print("Accuracy of Naive Bayes Model:",metrics.accuracy_score(Y_Test, Y_Pred_Test_nvb)*100)
161 | print("Accuracy of SVM Model:",metrics.accuracy_score(Y_Test,Y_Pred_Test_svm)*100)
162 | print(classification_report(Y_Test, Y_Pred_Test_svm))
163 | 


--------------------------------------------------------------------------------