generalized.py

#!/usr/bin/env python
# coding: utf-8
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
# from app import *


# location = input('Enter data location: ')
data = pd.read_csv(destination1)

type(data['LoanAmount'][0])


#extract numerical data columns
numerics = ['int16', 'int32', 'int64', 'float16', 'float32', 'float64']
newdf = data.select_dtypes(include=numerics)


#FIll missing values
for i in data.columns:
    data[i].fillna(data[i].mode()[0], inplace=True)



from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)


#


from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC


#


results = []
names = []
seed = 7
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=20, random_state=seed)
	cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)




# import mpld3


fig = plt.figure(figsize=(15,10))
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()


#


results = []
names = []
seed = 7
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=20, random_state=seed)
	cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)
#

# import mpld3


fig = plt.figure(figsize=(15,10))
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()


#

results = []
names = []
seed = 7
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=20, random_state=seed)
	cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)
#


results = []
names = []
seed = 7
scoring = 'accuracy'
for name, model in models:
	kfold = model_selection.KFold(n_splits=20, random_state=seed)
	cv_results = model_selection.cross_val_score(model, X, y, cv=kfold, scoring=scoring)
	results.append(cv_results)
	names.append(name)
	msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
	print(msg)