kilomileprediction.py

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

# In[ ]:


import tensorflow as tf
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import os

# print(os.getcwd())

#df = pd.read_csv('/mnt/batch/tasks/shared/LS_root/mounts/clusters/computeforaml/code/Users/luolala701/Kilometres-miles.csv')
# df.info
df = pd.read_csv('C://Users//luona//Downloads//Kilometres-miles.csv')


# In[10]:


#print('Painting the correlations')
#sns.scatterplot(df['Kilometres'], df['Miles'])
#plt.show()


# In[13]:


print('Define input(X) and output(Y) variables')
X_train = df['Kilometres']
Y_train = df['Miles']


# In[16]:


print('Creating the model')
model = tf.keras.Sequential()
model.add(tf.keras.layers.Dense(units=1, input_shape=[1]))


# In[17]:


print('Compiling the model')
model.compile(optimizer=tf.keras.optimizers.Adam(1), loss='mean_squared_error')


# In[18]:


print('Training the model')
epochs_hist = model.fit(X_train, Y_train, epochs = 250)


# In[19]:


print('Evaluating the model')
print(epochs_hist.history.keys())

#graph
plt.plot(epochs_hist.history['loss'])
plt.title('Evolution of the error associated with the model')
plt.xlabel('Epoch')
plt.ylabel('Training Loss')
plt.legend('Training Loss')
plt.show()


# In[20]:


kilometers = 100
predictedMiles = model.predict([kilometers])
print("The conversion from Kilometres to Miles is as follows: " + str(predictedMiles))


# In[21]:


milesByFormula = kilometers * 0.6214
print("The conversion from kilometers to miles using the mathematical formula is as follows:" + str(milesByFormula))
diference = milesByFormula - predictedMiles
print("Prediction error:" + str(diference))


# In[ ]: