filename = "[Link].
csv"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
data = read_csv(filename, names=names)
[Link](kind='density', subplots=True, figsize=(15,17),
layout=(3,3),sharex=False, sharey=False)
[Link]()
import pandas as pd #for handling datasets
import [Link] as sm #for statistical modeling
import pylab as pl #for plotting
import numpy as np #for numerical computation
pd.set_option('display.max_rows',None)
filename = "train_university_admission_data.csv"
names = ['admit','gre','gpa','prestige']
dfTrain = pd.read_csv(filename, names=names)
dfTest = pd.read_csv(filename, names=names)
import pandas as pd #for handling datasets
import [Link] as sm #for statistical modeling
import pylab as pl #for plotting
import numpy as np #for numerical computation
pd.set_option('display.max_rows',None)
filename = "D:\AIML-L2\Dataset\train_university_admission_data.csv"
names = ['admit','gre','gpa','prestige']
dfTrain = pd.read_csv(filename, names=names)
dfTest = pd.read_csv(filename, names=names)
admit gre gpa \
Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA Research
1 337 118 4 4.5 4.5 9.65 1
2 324 107 4 4 4.5 8.87 1
3 316 104 3 3 3.5 8 1
4 322 110 3 3.5 2.5 8.67 1
prestige
Serial No. GRE Score TOEFL Score University Rating SOP Chance of Admit
1 337 118 4 4.5 0.92
2 324 107 4 4 0.76
3 316 104 3 3 0.72
4 322 110 3 3.5 0.8
filename = "train_university_admission_data.csv"
names = ['admit','gre','gpa','prestige']
dfTrain = pd.read_csv(filename, names=names)
#dfTest = pd.read_csv(filename, names=names)
import pandas as pd #for handling datasets
import [Link] as sm #for statistical modeling
import pylab as pl #for plotting
import numpy as np #for numerical computation
pd.set_option('display.max_rows',None)
filename = "train_university_admission_data.csv"
names = ['admit','gre','gpa','prestige']
dfTrain = pd.read_csv(filename, names=names)
#dfTest = pd.read_csv(filename, names=names)
[Link]('prestige').size()
[Link]('admit').mean()
[Link]
COMPETENCY/Recordings/Forms/[Link]?id=%2Fsites%2Fku%2Dpractice
%2D4044%2FANALYTICS%2DCOMPETENCY%2FRecordings%2FNon%20Academy%2FAIML%2DPython%20for
%20DS%5FL1L2%2DGuru%2DMay20&viewid=aa63c8dc%2D8568%2D4868%2Daad3%2Def4ed0b40a5f
[Link]('prestige').mean()[['gre','gpa']]
print([Link](dfTrain['admit'], dfTrain['prestige'], rownames=['admit']))
[Link](['admit','prestige']).size()......we can also use this
[Link](dfTrain['admit'], dfTrain['prestige'], rownames=['admit']).unstack()
[Link](dfTrain['admit'], dfTrain['prestige'],
rownames=['Admit']).plot(kind='bar')
[Link](dfTrain['admit'], dfTrain['prestige'],
rownames=['Admit']).plot(kind='bar')
[Link](dfTrain['admit'],dfTrain['prestige'],rownames=['Admit'])
prestige best good ok veryGood
Admit
0 28 58 45 64
1 11 25 21 47
prestige best good ok veryGood
Admit
0 28 58 45 64
1 11 25 21 47
[Link](dfTrain['admit'], dfTrain['prestige'], rownames=['admit']).unstack()
.total() we'll add
[Link]('dftrain['admiy'].sum()
can you explain this command : [Link](dfTrain['admit'], dfTrain['prestige'],
rownames=['admit']).unstack()
from Sanjay to everyone:
[Link](dfTrain['admit'], dfTrain['prestige'], rownames=['admit'],
margins=True)
prestige best good ok veryGood All
admit
0 20 73 47 68 208
1 25 19 9 39 92
All 45 92 56 107 300
from Prashant Kumar to everyone:
print([Link](dfTrain['admit'], dfTrain['prestige'], rownames=['admit']).sum())
unstack() function?
from Shivansh Chaudhri to everyone:
dfTrain[dfTrain['admit']==0].sum()
from Gururajan Narasimhan to everyone:
[Link](dfTrain['admit'], dfTrain['prestige'],
rownames=['Admit']).plot(kind='bar')
print([Link](dfTrain['prestige'], dfTrain['admit'], rownames=['prestige']))
doing normalization:
----------------------
X = array[:,0:8]
Y = array[:,8]
scaler = Normalizer().fit(X)
normalizedX = [Link](X)
# summarize transformed data
set_printoptions(precision=3)
print(normalizedX[0:7,:])
doing standardization:
----------------------
X = array[:,0:8]
Y = array[:,8]
scaler = StandardScaler().fit(X)
rescaledX = [Link](X)
# summarize transformed data
set_printoptions(precision=3)
print(rescaledX[1:6,:])
Here, set_printoptions(precision=3) is used to display float numbers uptil 3rd
place after the point
X = array[:,0:8]
Y = array[:,8]
scaler = MinMaxScaler(feature_range=(10, 30))
rescaledX = scaler.fit_transform(X)
# summarize transformed data
set_printoptions(precision=4)
print(rescaledX[0:5,:])
X = array[:,0:8]
Y = array[:,8]
scaler = MinMaxScaler(feature_range=(10, 30))
rescaledX = scaler.fit_transform(X)
# summarize transformed data
set_printoptions(precision=4)
print(rescaledX[0:5,:])
peaor son is usied for the normal disctribution -- mostly used one
kinder and used for ranked distribution
peaor man -- is used for ranked and normal disctributed
what is the difference between correlation and similarity measure?
Correlation is to compareing the two diffrent values
similarity is a mesure for comaring as values