hello every one
i want to practice deep learning as descibed for a home price prediction problem
i use code as following
# IMPORTING PACKAGES
import pandas as pd # data processing
import numpy as np # working with arrays
import matplotlib.pyplot as plt # visualization
import seaborn as sb # visualization
from termcolor import colored as cl # text customization
from sklearn.model_selection import train_test_split # data split
from sklearn.linear_model import LinearRegression # OLS algorithm
from sklearn.linear_model import Ridge # Ridge algorithm
from sklearn.linear_model import Lasso # Lasso algorithm
from sklearn.linear_model import BayesianRidge # Bayesian algorithm
from sklearn.linear_model import ElasticNet # ElasticNet algorithm
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import explained_variance_score as evs # evaluation metric
from sklearn.metrics import r2_score as r2 # evaluation metric
from keras.models import Sequential
from keras.layers import Dense
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
import pandas as pd
from keras.callbacks import LearningRateScheduler
sb.set_style('whitegrid') # plot style
plt.rcParams['figure.figsize'] = (20, 10) # plot size
# IMPORTING DATA
from google.colab import files
uploaded = files.upload()
df = pd.read_csv('kc_house_data.csv')
df.set_index('id', inplace = True)
df.head(5)
df.dropna(inplace = True)
print(cl(df.isnull().sum(), attrs = ['bold']))
df.describe()
print(cl(df.dtypes, attrs = ['bold']))
df['price'] = pd.to_numeric(df['price'], errors = 'coerce')
df['price'] = df['price'].astype('int32')
#
df['bathrooms'] = pd.to_numeric(df['bathrooms'], errors = 'coerce')
df['bathrooms'] = df['bathrooms'].astype('int32')
#
df['floors'] = pd.to_numeric(df['floors'], errors = 'coerce')
df['floors'] = df['floors'].astype('int32')
#
df['lat'] = pd.to_numeric(df['lat'], errors = 'coerce')
df['lat'] = df['lat'].astype('int32')
#
df['long'] = pd.to_numeric(df['long'], errors = 'coerce')
df['long'] = df['long'].astype('int32')
#
print(cl(df.dtypes, attrs = ['bold']))
dataset=df.values
dataset
X=dataset[:,1:19]
Y=dataset[:,1]
print(Y)
min_max_scaler=MinMaxScaler()
X_scale = min_max_scaler.fit_transform(X)
X_scale
X_train,X_val_and_test,Y_train,Y_val_and_test = train_test_split(X_scale,Y, test_size=0.2)
X_val, X_test,Y_val,Y_test=train_test_split(X_val_and_test,Y_val_and_test,test_size=0.5)
print(X_train.shape, X_val.shape, X_test.shape, Y_train.shape, Y_val.shape, Y_test.shape)
model=Sequential()
model.add(Dense(units=32, activation = 'relu', input_dim=18))
model.add(Dense(units=32,activation='relu'))
model.add(Dense(units=32,activation='relu'))
model.add(Dense(units=1,activation='sigmoid'))
model.compile(optimizer='sgd',
loss='binary_crossentropy',
metrics=['accuracy'])
X_train = np.asarray(X_train).astype('float32')
Y_train = np.asarray(Y_train).astype('float32')
X_val = np.asarray(X_val).astype('float32')
Y_val = np.asarray(Y_val).astype('float32')
X_test = np.asarray(X_test).astype('float32')
Y_test = np.asarray(Y_test).astype('float32')
hist = model.fit(
X_train, Y_train,
batch_size=32, epochs=5,
validation_data=(X_val, Y_val)
)
but in last model.hit stage i get zero accuracy and nan loss values from the fırst epoch
what is the problem and how i could fix that
here is the dataset and screen shot of last results
- Badges
- Science topic