#!/usr/bin/env python
# coding: utf-8

# # Lecture 28 Code
# ## Yue Li

# ## Hand-wrriten MNIST digits

# In[ ]:


# pip install python-mnist # uncomment this to install python-mnist


# In[ ]:


from mnist import MNIST

mndata = MNIST('mnist')

images, labels = mndata.load_training()


# In[ ]:


print(type(images))
# display the first `2' in the data
for index,digit in enumerate(labels):
    if digit == 2:
        break
print(mndata.display(images[index]))


# In[ ]:


print(len(images[index]))


# In[ ]:


print(len(images[index])/28)


# ## Linear regression

# In[ ]:


# pip install sklearn # comment out this line to install


# In[8]:


import numpy as np 
from sklearn import linear_model
import matplotlib.pyplot as plt 


# Generate some random data for training the linear regression model

# In[4]:


# Genrating random linear data 
# There will be 50 data points ranging from 0 to 50 
x = np.linspace(0, 50, 50) 
y = np.linspace(0, 50, 50) 
  
# Adding noise to the random linear data 
x += np.random.uniform(-4, 4, 50) 
y += np.random.uniform(-4, 4, 50) 
  
n = len(x) # Number of data points 


# In[7]:


plt.scatter(x, y) 
plt.xlabel('Input x') 
plt.ylabel('Output y') 
plt.title("Training Data") 
plt.show()


# In[18]:


reg = linear_model.LinearRegression()
x1 = [[i] for i in x] # make a 2D list with each data point as a list
reg.fit(x1, y)
y1 = reg.predict(x1)


# In[20]:


# Plotting the Results 
plt.plot(x, y, 'ro', label ='Original data') 
plt.plot(x, y1, label ='Fitted line') 
plt.title('Linear Regression Result')
plt.xlabel('Input x') 
plt.ylabel('Output y') 
plt.legend() 
plt.show() 


# In[ ]:


# pip install tensorflow # comment out this line to install


# In[21]:


import tensorflow as tf
mnist = tf.keras.datasets.mnist

(x_train, y_train),(x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test)


# In[ ]: