ShrashtiSinghal

S.No.,	  Group Name,	                    Group Link,                                              Number of Members in K*,	 Social Media,	 Average Rating
3,	      Data Science - R & Python,	    https://www.facebook.com/groups/AnalyticsEdge/,                                                                      217,	  Facebook,	   88.7
5,	      Data Science,	                       https://www.facebook.com/groups/DataScienceGroup/,                                                               137,	 Facebook	,   88.6
15,	    Data Science with Python,	     https://www.facebook.com/groups/1006538092836222/,                                                                     56.5,	Facebook,	84.5
6,	      Machine Learning and Data Science,	   https://www.linkedin.com/groups/4298680/,                                                               128,	Linkedin,	68.34
13,	    Python Data Science and Machine Learning,	    https://www.linkedin.com/groups/4388870/,                                                      63,	L

ShrashtiSinghal

#Cross Validation

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.model_selection import RepeatedKFold
from sklearn.model_selection import cross_val_score
import seaborn as sns
from sklearn.linear_model import LinearRegression, Lasso,ElasticNet, Ridge, MultiTaskLasso, LassoLars, OrthogonalMatchingPursuit
from sklearn.model_selection import train_test_split

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

#Regularization

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression, Lasso,ElasticNet, Ridge, MultiTaskLasso, LassoLars, OrthogonalMatchingPursuit
from sklearn.model_selection import train_test_split
from sklearn import metrics

ShrashtiSinghal

#Test Train Split

import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn import metrics

class predit:
    def bestFitLine(self):

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

#Log Transformation to remove skewness
y =  np.log1p(y)
for col in x.columns:
    if np.abs(x[col].skew()) > 0.3:
        x[col] = np.log1p(x[col])

ShrashtiSinghal

#Scale all the attributes except RAD, CHAS, ZN
from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
header_new = ['CRIM', 'INDUS', 'NOX', 'RM', 'AGE','DIS','TAX', 'PTRATIO','B','LSTAT']
x = data.loc[:,header_new]
y = data['MEDV']
x = pd.DataFrame(data=min_max_scaler.fit_transform(x), columns=header_new)

ShrashtiSinghal

   #Find Percentage of outliers in every column
   for k, v in data.items():
        q1 = v.quantile(0.25)
        q3 = v.quantile(0.75)
        IQR = q3 - q1
        v_col = v[(v <= q1 - 1.5 * IQR) | (v >= q3 + 1.5 * IQR)]
        percentage = np.shape(v_col)[0] * 100.0 / np.shape(data)[0]
        print("Column %s outliers = %.2f%%" % (k, percentage))