ShrashtiSinghal

#Check data for skewness
fig, axs = plt.subplots(ncols=7, nrows=2, figsize=(20, 10))
index = 0
axs = axs.flatten()
for k,v in data.items():
    sns.distplot(v, ax=axs[index], color="green")
    index += 1
plt.tight_layout(pad=0.4, w_pad=0.5, h_pad=5.0)

ShrashtiSinghal

#Analyse the data
import numpy as np # linear algebra
import pandas as pd # data processing, CSV file
from pandas import read_csv
import seaborn as sns
import matplotlib.pyplot as plt
from scipy import stats

header = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']
df = read_csv('housing.csv', header=None, delimiter=r"\s+", names=header)

ShrashtiSinghal

#Load & Format CSV, Set Tain & Test Split
import pandas as pd
import numpy as np
from sklearn import datasets, linear_model
from sklearn.model_selection import train_test_split

file="housing.csv"                                                                                                                      #load CSV
header = ['CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', 'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV']                      #name columns
df=pd.read_csv(file, header=None, delimiter=r"\s+", names=header)                                                                       #format downloaded CSV in dataframe
print(df.head())

ShrashtiSinghal

# 10.c Evalute Model Performance after Boxcox Transformation

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from scipy import stats
import seaborn as sns
from scipy.special import boxcox, inv_boxcox

ShrashtiSinghal

# 7.c. Identify Skewed Data

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from scipy.stats import norm

class predit:
    def bestFitLine(self):
        size=np.array([1491,1526,1533,1680,1680,1869,1890,1920,1936,1950,1953,2016,2117,3072,3182,3196]).reshape(-1,1)

ShrashtiSinghal

#7.b. Identify Outliers in a dataset

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns


class predit:
    def bestFitLine(self):
        size=np.array([1300,1491,1526,1533,1680,1680,1869,1890,1920,1936,1950,1953,2016,2117,3072,3182,3196,3842,5925,7879,9000])

ShrashtiSinghal

#2.	Code a machine Learning program from scratch - House Price Prediction
#2.a Predict prices for a list of houses

newHouseSize= np.array([2268,2280,2628,2645,3000])                  #Update a single size with list of sizes
for size, cost in zip(newHouseSize, price):
    print ("Price of {} sq feet house is: {}".format(size, cost))   #Format the ouput

ShrashtiSinghal

import numpy as np
from sklearn.linear_model import LinearRegression

class predit:
    def bestFitLine(self,data):
        size=np.array([500,650,700,780,900,1100,1150,2000,2200,2500]).reshape(-1,1)
        price=np.array([1000,1500,1600,1770,2200,3000,3500,4400,4600,6000]).reshape(-1,1)

        regressionLine=LinearRegression().fit(size,price)
        pred=regressionLine.predict(size)

ShrashtiSinghal

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

class predit:
    def bestFitLine(self,data):
        size=np.array([500,650,700,780,900,1100,1150,2000,2200,2500]).reshape(-1,1)
        price=np.array([1000,1500,1600,1770,2200,3000,3500,4400,4600,6000]).reshape(-1,1)

        regressionLine=LinearRegression().fit(size,price)

ShrashtiSinghal

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

class predit:
    def bestFitLine(self):
        size=np.array([500,650,700,780,900,1100,1150,2000,2200,2500]).reshape(-1,1)
        price=np.array([1000,1500,1600,1770,2200,3000,3500,4400,4600,6000]).reshape(-1,1)

        regressionLine=LinearRegression().fit(size,price)