from sklearn.naive_bayes import MultinomialNB as MB from sklearn.naive_bayes import GaussianNB as GB ##Building the Multinomial Naive Bayes Model classifier_mb = MB() classifier_mb.fit(x_train, y_train) pred_mb = classifier_mb.predict(x_train) accuracy_mb_train = np.mean(pred_mb == y_train) ##77% pd.crosstab(pred_mb, y_train) ##for test data pred_mb_test = classifier_mb.predict(x_test) accuracy_mb_test = np.mean(pred_mb_test == y_test) ##77% pd.crosstab(pred_mb_test, y_test) ##Building Gaussian model classifier_gb = GB() classifier_gb.fit(x_train, y_train) pred_gb = classifier_gb.predict(x_train) accuracy_gb_train = np.mean(pred_gb == y_train) ##80% pd.crosstab(pred_gb, y_train) ##for test data pred_gb_train = classifier_gb.predict(x_test) accuracy_gb_test = np.mean(pred_gb_train == y_test) ##80% pd.crosstab(pred_gb_train, y_test)
Chris has label 1
"""
import sys
from time import time
sys.path.append("../tools/")
from email_preprocess import preprocess
### features_train and features_test are the features for the training
### and testing datasets, respectively
### labels_train and labels_test are the corresponding item labels
features_train, features_test, labels_train, labels_test = preprocess()
#########################################################
### your code goes here ###
from sklearn.naive_bayes import GaussianNB as GB
clf = GB()
t0 = time()
clf.fit(features_train, labels_train)
print("training time:", round(time() - t0, 3), "s")
t1 = time()
clf.predict(features_train)
print("predicting time:", round(time() - t1, 3), "s")
accuracy_score = clf.score(features_test, labels_test)
print(accuracy_score)
#########################################################
'average_montly_hours', 'last_evaluation'
]
print(Important_features)
Pred_var = ["left"]
print(Pred_var)
# In[ ]:
# Lets us make a list of models
models = [
"RandomForestClassifier", "Gaussian Naive Bays", "KNN",
"Logistic_Regression", "Support_Vector"
]
Classification_models = [
RandomForestClassifier(n_estimators=100),
GB(),
knn(n_neighbors=7),
LogisticRegression(),
SVC()
]
Model_Accuracy = []
for model in Classification_models:
Accuracy = Classification_model(model, Data, All_features, Pred_var)
Model_Accuracy.append(Accuracy)
# In[ ]:
Accuracy_with_all_features = pd.DataFrame({
"Classification Model":
models,
"Accuracy with all features":
#%% DecisionTree
from sklearn.tree import DecisionTreeClassifier as DT
dt = DT(criterion="entropy")
dt.fit(x, y)
dt.predict(x)
pde = dt.predict_proba(x)
print("DTE accuracy", dt.score(x, y))
dt = DT(criterion="gini")
dt.fit(x, y)
dt.predict(x)
pdg = dt.predict_proba(x)
print("DTG accuracy", dt.score(x, y))
# z = dt.predict([[40, 1, 15,14, 55, 5.5, 0.856075, 2.16892]])
####!!!task 2 there are two criterions on dcisiontree model, gini and entropy, try to understand the difference
####!!!task 3 try these two dcisiontree models on banloan default problem
from sklearn.naive_bayes import GaussianNB as GB
gb = GB()
gb.fit(x, y)
gb.predict(x)
pgb = gb.predict_proba(x)
print("NB accuracy", gb.score(x, y))
from sklearn.svm import SVC
svc = SVC()
svc.fit(x, y)
svc.predict(x)
print("svc accuracy", svc.score(x, y))
classifier_nb = MB() classifier_nb.fit(train_emails_matrix, y_train) train_pred_nb = classifier_nb.predict(train_emails_matrix) accuracy_nb = np.mean(train_pred_nb == y_train) ##98.8% pd.crosstab(train_pred_nb, y_train) ##predicting on test data test_pred_nb = classifier_nb.predict(test_emails_matrix) accuracy_test_nb = np.mean(test_pred_nb == y_test) ##96.82% pd.crosstab(test_pred_nb, y_test) ##Building Gaussian model classifier_gb = GB() classifier_gb.fit(train_emails_matrix.toarray(), y_train.values) train_pred_gb = classifier_gb.predict(train_emails_matrix.toarray()) accuracy_gb = np.mean(train_pred_gb == y_train) ##92% pd.crosstab(train_pred_gb, y_train) ##predicting on test data test_pred_gb = classifier_gb.predict(test_emails_matrix.toarray()) accuracy_test_gb = np.mean(test_pred_gb == y_test) ##85% pd.crosstab(test_pred_gb, y_test) ###Building with TFIDF transformation tfidf_transformer = TfidfTransformer().fit(all_emails_matrix)
x_train=salary_train.iloc[:,0:12] y_train=salary_train.iloc[:,13] x_test=salary_test.iloc[:,0:12] y_test=salary_test.iloc[:,13] #######Importing the navies bayes function###### from sklearn.naive_bayes import MultinomialNB as MB from sklearn.naive_bayes import GaussianNB as GB classifiers_mb=MB() classifiers_mb.fit(x_train,y_train) train_pred_mb=classifiers_mb.predict(x_train) train_accu_mb=np.mean(train_pred_mb==y_train)##77% pd.crosstab(train_pred_mb,y_train) test_pred_mb=classifiers_mb.predict(x_test) test_accu_mb=np.mean(test_pred_mb==y_test)##77% pd.crosstab(test_pred_mb,y_test) classifiers_gb=GB() classifiers_gb.fit(x_train,y_train) train_pred_gb=classifiers_gb.predict(x_train) train_accu_gb=np.mean(train_pred_gb==y_train)##80% pd.crosstab(train_pred_gb,y_train) test_pred_gb=classifiers_gb.predict(x_test) test_accu_gb=np.mean(test_pred_gb==y_test)##80% #####From above Gassian Navies bayes contian more accuracy w.r.t. multinomial NB.
def crossRun(self):
window = Toplevel(self)
ttk.Label(window, text='Result').grid(column=0, row=0, sticky=W)
self.crossResult = ScrolledText(window, height=15, width=70)
self.crossResult.grid(column=0,
row=1,
sticky=W,
columnspan=10,
rowspan=5)
self.crossResult.config(state=DISABLED)
from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier as knn
from sklearn.naive_bayes import GaussianNB as GB
from sklearn.svm import SVC
from sklearn.model_selection import cross_validate
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler
df_drop = df.drop(labels=['sales', 'salary'], axis=1)
left_col = df_drop['left']
df_drop.drop(labels=['left'], axis=1, inplace=True)
df_drop.insert(0, 'left', left_col)
df_drop.head()
X = df_drop.iloc[:, 1:8].values
y = df_drop.iloc[:, 0].values
X_std = StandardScaler().fit_transform(X)
sklearn_pca = PCA(n_components=6)
X_pca = sklearn_pca.fit_transform(X_std)
models = [
"RandomForestClassifier", "Gaussian Naive Bays", "KNN",
"Logistic_Regression", "Support_Vector"
]
Classification_models = [
RandomForestClassifier(n_estimators=100),
GB(),
knn(n_neighbors=7),
LogisticRegression(),
SVC()
]
Model_Accuracy = []
scoring = {
'acc': 'accuracy',
'f1': 'f1',
'precision': 'precision',
'recall': 'recall',
'roc_auc': 'roc_auc'
}
for model, model_name in zip(Classification_models, models):
print(model_name)
scores = cross_validate(model,
X_pca,
y,
scoring=scoring,
cv=10,
return_train_score=True)
Model_Accuracy.append(scores)
self.crossResult.config(state=NORMAL)
self.crossResult.delete(1.0, END)
for i, m in zip(Model_Accuracy, models):
self.crossResult.insert(END, "\n" + m)
self.crossResult.insert(END, "\n--------\n")
for j in i:
self.crossResult.insert(
END,
str(j) + ": " + str(i[j].mean()) + "\n")
self.crossResult.config(state=DISABLED)
print(final_test_df)
train_X = final_train_df.iloc[:, 0:13]
train_y = final_train_df.iloc[:, 13]
print(train_X.head())
print(train_y.head())
input()
test_X = final_test_df.iloc[:, 0:13]
test_y = final_test_df.iloc[:, 13]
print(test_X.head())
print(test_y.head())
input()
# Naive Bayes model
ignb = GB()
imnb = MB()
# Building and predicting at the same time
pred_gnb = ignb.fit(train_X, train_y).predict(test_X) # GaussianNB model
pred_mnb = imnb.fit(train_X, train_y).predict(test_X) # Multinomal model
# Confusion matrix GaussianNB model
print(confusion_matrix(test_y, pred_gnb))
print(pd.crosstab(test_y.values.flatten(), pred_gnb))
print(classification_report(test_y, pred_gnb)) # classification report
print(np.mean(
pred_gnb == test_y.values.flatten())) #>> Accuracy = 0.7946879150066402
input()
# Confusion matrix Multinomal model