def pr_curve_plot(self,test_array,prediction_prob,title,categories=[]):
if len(categories)<1:
categories=self.categories
fig = plt.figure(figsize=(10,7))
ax1 = fig.add_subplot(111)
precision=dict();recall=dict();average_precision = dict()
for i in range(len(categories)):
precision[i], recall[i], _ = precision_recall_curve(test_array[:, i],
prediction_prob[:, i])
average_precision[i] = average_precision_score(test_array[:, i],
prediction_prob[:, i])
precision["micro"], recall["micro"], _ = precision_recall_curve(test_array.ravel(),
prediction_prob.ravel())
average_precision["micro"] = average_precision_score(test_array, prediction_prob,
average="micro")
plt.plot(recall["micro"], precision["micro"],lw=6,
label='Average Precision-recall curve (area = {0:0.2f})'
''.format(average_precision["micro"]))
for i in range(len(categories)):
plt.plot(recall[i], precision[i],'--',lw=4,
label='Precision-recall curve of class {0} (area = {1:0.2f})'
''.format(categories[i], average_precision[i]))
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('Recall',fontsize=18)
plt.ylabel('Precision',fontsize=18)
plt.legend(bbox_to_anchor=(1.1, 1.05),fontsize=14)
plt.title('Precision vs Recall',fontsize=18)
ax1.tick_params(axis='both', which='major', labelsize=16)
plt.style('ggplot')
fig.savefig(self.results+title+'pr.png', dpi=fig.dpi,bbox_inches='tight')
plt.close()
def roc_curve_plot(self,test_array,prediction_prob,title,categories=[]):
if len(categories)<1:
categories=self.categories
fig = plt.figure(figsize=(10,7))
ax1 = fig.add_subplot(111)
fpr=dict();tpr=dict();average_roc_auc = dict();roc_auc=dict()
for i in range(len(categories)):
fpr[i], tpr[i], _ = roc_curve(test_array[:, i], prediction_prob[:, i])
roc_auc[i] = auc(fpr[i], tpr[i])
average_roc_auc[i] = roc_auc_score(test_array[:, i],
prediction_prob[:, i])
fpr["micro"], tpr["micro"], _ = roc_curve(test_array.ravel(),
prediction_prob.ravel())
average_roc_auc["micro"] = roc_auc_score(test_array, prediction_prob,
average="micro")
plt.plot(fpr["micro"], tpr["micro"],lw=6,
label='Average ROC curve (area = {0:0.2f})'
''.format(average_roc_auc["micro"]))
for i in range(len(categories)):
plt.plot(fpr[i], tpr[i],'--',lw=4,
label='ROC curve of class {0} (area = {1:0.2f})'
''.format(categories[i], average_roc_auc[i]))
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate',fontsize=18)
plt.ylabel('True Positive Rate',fontsize=18)
plt.legend(bbox_to_anchor=(1.1, 1.05),fontsize=14)
ax1.tick_params(axis='both', which='major', labelsize=16)
plt.title('Receiver operating characteristics',fontsize=18)
plt.style('ggplot')
fig.savefig(self.results+title+'roc.png', dpi=fig.dpi,bbox_inches='tight')
plt.close()
#make prediction
print("[INFO] Evaluating network...")
preIdxs = model.predict(testX, batch_size=BS)
print(preIdxs)
#find the index with largest predicted probability
preIdxs = np.argmax(preIdxs, axis=1)
#classification report
print(
classification_report(testY.argmax(axis=1),
preIdxs,
target_names=lb.classes_))
#serialize the model to disk
print("[INFO] Saving mask detector model...")
model.save(args["model"], save_format="h5")
#plot the training loss and accuracy
N = EPOCHS
plt.style("ggplot")
plt.figure()
plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, N), H.history["accuracy"], label="train_acc")
plt.plot(np.arange(0, N), H.history["val_accuracy"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="lower left")
plt.savefig(args["plot"])
# -*- coding: utf-8 -*-
"""
Created on Wed Jan 22 02:59:43 2020
@author: Regaip
"""
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
veri = pd.read_csv("Borçlar.csv", sep=";", index_col=0)
veri_2017 = veri.iloc[0:12, ]
veri_2018 = veri.iloc[12:24, ]
veri_2019 = veri.iloc[24:, ]
plt.style("whitegrid")
plt.figure(figsize=(15, 10))
plt.bar(veri.index, veri["Toplam"], label="Toplam")
plt.bar(veri.index, veri["Anapara"], label="Anapara")
plt.bar(veri.index, veri["Faiz"], label="Faiz")
plt.legend()
plt.xticks(veri.index, rotation='vertical')
plt.title("Merkezi Yönetim Dış Borç Ödemeleri", fontdict={"size": 20})
plt.xlabel("Aylar ve Yıllar", fontdict={"size": 15})
plt.ylabel("Ödeme Miktarı \nMilyon $", fontdict={"size": 15})
#plt.margins(0.1)
# Tweak spacing to prevent clipping of tick-labels
plt.subplots_adjust(bottom=0.1)
plt.show()
import numpy as np
from sklearn import linear_model
from sklearn.svm import SVR
from sklearn.model_selection import train_test_split
import pandas as pd
import matplotlib.pyplot as plt
plt.style('ggplot')
def linear_mode():
dataTrain = pd.read_csv("/Users/senora/Desktop/train.csv")
dataTest = pd.read_csv("/Users/senora/Desktop/test.csv")
x_train = dataTrain[[
'METEOROLOGICAL DROUGHT', 'HYDROLOGICAL DROUGHT',
'AGRICULTURAL DROUGHT', 'AREA UNDER CULTIVATION'
]]
y_train = dataTrain[['YIELD']]
x_test = dataTest[[
'METEOROLOGICAL DROUGHT', 'HYDROLOGICAL DROUGHT',
'AGRICULTURAL DROUGHT', 'AREA UNDER CULTIVATION'
]]
y_test = dataTest[['YIELD']]
ols = linear_model.LinearRegression()
model = ols.fit(x_train, y_train)
accuracy = ols.score(x_test, y_test)
return ols, model
# Autoencoder with Pytroch using fashion MNIST dataset.
import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision.datasets as dsets
import matplotlib.pyplot as plt
import numpy
figsize = (15, 6)
plt.style('fivethirtyeight')
# 1. Load Dataset
train_dataset = dsets.FashionMNIST(root='./data',
train=True,
transforms=transforms.ToTensor(),
download=True)
test_dataset = dsets.FashionMNIST(root='./data',
train=False,
transforms=transforms.ToTensor(),
download=True)
# 2. Data Loader
batch_size = 100
n_iters = 5000
num_epochs = n_iters / (len(train_dataset) / batch_size)
num_epochs = int(num_epochs)