티스토리 뷰
FASHION MNIST with Python (DAY 6)¶
DATA SOURCE : https://www.kaggle.com/zalando-research/fashionmnist (Kaggle, Fashion MNIST)
FASHION MNIST with Python (DAY 1) : http://deepstat.tistory.com/35
FASHION MNIST with Python (DAY 2) : http://deepstat.tistory.com/36
FASHION MNIST with Python (DAY 3) : http://deepstat.tistory.com/37
FASHION MNIST with Python (DAY 4) : http://deepstat.tistory.com/38
FASHION MNIST with Python (DAY 5) : http://deepstat.tistory.com/39
Datasets¶
Importing numpy, pandas, pyplot¶
In [1]:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
Loading datasets¶
In [2]:
data_train = pd.read_csv("..\\datasets\\fashion-mnist_train.csv")
data_test = pd.read_csv("..\\datasets\\fashion-mnist_test.csv")
In [3]:
data_train_y = data_train.label
y_test = data_test.label
In [4]:
data_train_x = data_train.drop("label",axis=1)/256
x_test = data_test.drop("label",axis=1)/256
Spliting valid and training¶
In [5]:
np.random.seed(0)
valid2_idx = np.random.choice(60000,10000,replace = False)
valid1_idx = np.random.choice(list(set(range(60000)) - set(valid2_idx)),10000,replace=False)
train_idx = list(set(range(60000))-set(valid1_idx)-set(valid2_idx))
x_train = data_train_x.iloc[train_idx,:]
y_train = data_train_y.iloc[train_idx]
x_valid1 = data_train_x.iloc[valid1_idx,:]
y_valid1 = data_train_y.iloc[valid1_idx]
x_valid2 = data_train_x.iloc[valid2_idx,:]
y_valid2 = data_train_y.iloc[valid2_idx]
Linear Discriminant Analysis (LDA)¶
Importing LinearDiscriminantAnalysis¶
In [6]:
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.metrics import confusion_matrix
Fitting LinearDiscriminantAnalysis¶
In [7]:
LDA_model = LinearDiscriminantAnalysis().fit(x_train, y_train)
Training Accuracy¶
In [8]:
confusion_matrix(LDA_model.predict(x_train),y_train)
Out[8]:
In [9]:
LDA_model_train_acc = (LDA_model.predict(x_train) == y_train).mean()
print("TRAINING ACCURACY =",LDA_model_train_acc)
Validation Accuracy¶
In [10]:
confusion_matrix(LDA_model.predict(x_valid1),y_valid1)
Out[10]:
In [11]:
LDA_model_valid1_acc = (LDA_model.predict(x_valid1) == y_valid1).mean()
print("VALIDATION ACCURACY =",LDA_model_valid1_acc)
In [12]:
{"TRAIN_ACC" : LDA_model_train_acc , "VALID_ACC" : LDA_model_valid1_acc}
Out[12]:
Fitting LinearDiscriminantAnalysis with shrinkage and solver 'lsqr'¶
In [13]:
LDA_model_with_shrinkage_lsqr = LinearDiscriminantAnalysis(solver='lsqr',shrinkage="auto").fit(x_train, y_train)
Training Accuracy¶
In [14]:
confusion_matrix(LDA_model_with_shrinkage_lsqr.predict(x_train),y_train)
Out[14]:
In [15]:
LDA_model_with_shrinkage_lsqr_train_acc = (LDA_model_with_shrinkage_lsqr.predict(x_train) == y_train).mean()
print("TRAINING ACCURACY =",LDA_model_with_shrinkage_lsqr_train_acc)
Validation Accuracy¶
In [16]:
confusion_matrix(LDA_model_with_shrinkage_lsqr.predict(x_valid1),y_valid1)
Out[16]:
In [17]:
LDA_model_with_shrinkage_lsqr_valid1_acc = (LDA_model_with_shrinkage_lsqr.predict(x_valid1) == y_valid1).mean()
print("VALIDATION ACCURACY =",LDA_model_with_shrinkage_lsqr_valid1_acc)
In [18]:
{"TRAIN_ACC" : LDA_model_with_shrinkage_lsqr_train_acc , "VALID_ACC" : LDA_model_with_shrinkage_lsqr_valid1_acc}
Out[18]:
Fitting LinearDiscriminantAnalysis with shrinkage and solver 'eigen'¶
In [19]:
LDA_model_with_shrinkage_eigen = LinearDiscriminantAnalysis(solver='eigen',shrinkage="auto").fit(x_train, y_train)
Training Accuracy¶
In [20]:
confusion_matrix(LDA_model_with_shrinkage_eigen.predict(x_train),y_train)
Out[20]:
In [21]:
LDA_model_with_shrinkage_eigen_train_acc = (LDA_model_with_shrinkage_eigen.predict(x_train) == y_train).mean()
print("TRAINING ACCURACY =",LDA_model_with_shrinkage_eigen_train_acc)
Validation Accuracy¶
In [22]:
confusion_matrix(LDA_model_with_shrinkage_eigen.predict(x_valid1),y_valid1)
Out[22]:
In [23]:
LDA_model_with_shrinkage_eigen_valid1_acc = (LDA_model_with_shrinkage_eigen.predict(x_valid1) == y_valid1).mean()
print("VALIDATION ACCURACY =",LDA_model_with_shrinkage_eigen_valid1_acc)
In [24]:
{"TRAIN_ACC" : LDA_model_with_shrinkage_eigen_train_acc , "VALID_ACC" : LDA_model_with_shrinkage_eigen_valid1_acc}
Out[24]:
Quadratic Discriminant Analysis (QDA)¶
Importing QuadraticDiscriminantAnalysis¶
In [25]:
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.metrics import confusion_matrix
Fitting QDA¶
In [26]:
QDA_model = QuadraticDiscriminantAnalysis().fit(x_train, y_train)
Training Accuracy¶
In [27]:
confusion_matrix(QDA_model.predict(x_train),y_train)
Out[27]:
In [28]:
QDA_model_train_acc = (QDA_model.predict(x_train) == y_train).mean()
print("TRAINING ACCURACY =",QDA_model_train_acc)
Validation Accuracy¶
In [29]:
confusion_matrix(QDA_model.predict(x_valid1),y_valid1)
Out[29]:
In [30]:
QDA_model_valid1_acc = (QDA_model.predict(x_valid1) == y_valid1).mean()
print("VALIDATION ACCURACY =",QDA_model_valid1_acc)
In [31]:
{"TRAIN_ACC" : QDA_model_train_acc , "VALID_ACC" : QDA_model_valid1_acc}
Out[31]:
'Real Data Analysis' 카테고리의 다른 글
| FASHION MNIST with Python (DAY 8) - CNN (0) | 2018.08.26 |
|---|---|
| FASHION MNIST with Python (DAY 7) - MLP (0) | 2018.08.22 |
| FASHION MNIST with Python (DAY 5) - knn (0) | 2018.08.19 |
| FASHION MNIST with Python (DAY 4) - support vector machine (0) | 2018.08.18 |
| FASHION MNIST with Python (DAY 3) - 1. gradient boosting, 2. adaboosting (0) | 2018.08.16 |