dl1.txt

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

-----------------------------------
#Lets load the dataset and sample some
column_names = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'PRICE']
df = pd.read_csv('housing.csv', header=None, delimiter=r"\s+", names=column_names)

-----------------------------------
df.head(5)
-----------------------------------

# Dimension of the dataset
df.shape
-----------------------------------

# Let's summarize the data to see the distribution of data
df.describe()
-----------------------------------
import seaborn as sns
import matplotlib.pyplot as plt
from scipy import stats

fig, axs = plt.subplots(ncols=7, nrows=2, figsize=(20, 10))
index = 0
axs = axs.flatten()
for k,v in df.items():
    sns.boxplot(y=k, data=df, ax=axs[index])
    index += 1
plt.tight_layout(pad=0.4, w_pad=0.5, h_pad=5.0)

-----------------------------------
for k, v in df.items():
    q1 = v.quantile(0.25)
    q3 = v.quantile(0.75)
    irq = q3 - q1
    v_col = v[(v <= q1 - 1.5 * irq) | (v >= q3 + 1.5 * irq)]
    perc = np.shape(v_col)[0] * 100.0 / np.shape(df)[0]
    print("Column %s outliers = %.2f%%" % (k, perc))

-----------------------------------
df = df[~(df['PRICE'] >= 35.0)]
print(np.shape(df))

-----------------------------------
#Looking at the data with names and target variable
df.head()

-----------------------------------
#Shape of the data
print(df.shape)

-----------------------------------
#Checking the null values in the dataset
df.isnull().sum()

-----------------------------------
# No null values in the dataset, no missing value treatement needed

-----------------------------------
#Checking the statistics of the data
df.describe()

-----------------------------------
df.info()

-----------------------------------
#checking the distribution of the target variable
import seaborn as sns
sns.histplot(df.PRICE , kde = True)

-----------------------------------
#Distribution using box plot
sns.boxplot(df.PRICE)

-----------------------------------
#checking Correlation of the data 
correlation = df.corr()
correlation.loc['PRICE']

-----------------------------------
# plotting the heatmap
import matplotlib.pyplot as plt
fig,axes = plt.subplots(figsize=(15,12))
sns.heatmap(correlation,square = True,annot = True)

-----------------------------------
# Checking the scatter plot with the most correlated features
plt.figure(figsize = (20,5))
features = ['LSTAT','RM','PTRATIO']
for i, col in enumerate(features):
    plt.subplot(1, len(features) , i+1)
    x = df[col]
    y = df.PRICE
    plt.scatter(x, y, marker='o')
    plt.title("Variation in House prices")
    plt.xlabel(col)
    plt.ylabel('"House prices in $1000"')

-----------------------------------
#X = data[['LSTAT','RM','PTRATIO']]
X = df.iloc[:,:-1]
y= df.PRICE

-----------------------------------
# Splitting the data into train and test for building the model
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.2, random_state = 4)

-----------------------------------
#Linear Regression 
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()

-----------------------------------
#Fitting the model
regressor.fit(X_train,y_train)

-----------------------------------
#Prediction on the test dataset
y_pred = regressor.predict(X_test)

-----------------------------------
# Predicting RMSE the Test set results
from sklearn.metrics import mean_squared_error
rmse = (np.sqrt(mean_squared_error(y_test, y_pred)))
print(rmse)

-----------------------------------
from sklearn.metrics import r2_score
r2 = r2_score(y_test, y_pred)
print(r2)

-----------------------------------
#Scaling the dataset
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)

-----------------------------------
#Creating the neural network model
import keras
from keras.layers import Dense, Activation,Dropout
from keras.models import Sequential

model = Sequential()

model.add(Dense(128,activation  = 'relu',input_dim =13))
model.add(Dense(64,activation  = 'relu'))
model.add(Dense(32,activation  = 'relu'))
model.add(Dense(16,activation  = 'relu'))
model.add(Dense(1))
model.compile(optimizer = 'adam',loss = 'mean_squared_error')

-----------------------------------
model.fit(X_train, y_train, epochs = 100)

-----------------------------------
y_pred = model.predict(X_test)

-----------------------------------
from sklearn.metrics import r2_score
r2 = r2_score(y_test, y_pred)
print(r2)

-----------------------------------
# Predicting RMSE the Test set results
from sklearn.metrics import mean_squared_error
rmse = (np.sqrt(mean_squared_error(y_test, y_pred)))
print(rmse)