/
CollegeTypeClassification(TreeMethodsSpark).py
155 lines (76 loc) · 2.46 KB
/
CollegeTypeClassification(TreeMethodsSpark).py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
# Databricks notebook source
from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('TreeForCollege').getOrCreate()
df = spark.read.csv('/FileStore/tables/College.csv',header=True,inferSchema=True)
df.show()
df.columns
df.printSchema()
from pyspark.ml.feature import VectorAssembler
assembler = VectorAssembler(inputCols=['Apps',
'Accept',
'Enroll',
'Top10perc',
'Top25perc',
'F_Undergrad',
'P_Undergrad',
'Outstate',
'Room_Board',
'Books',
'Personal',
'PhD',
'Terminal',
'S_F_Ratio',
'perc_alumni',
'Expend',
'Grad_Rate'], outputCol='features')
output = assembler.transform(df)
from pyspark.ml.feature import StringIndexer
indexer = StringIndexer(inputCol='Private',outputCol='PrivateIndex')
outputFixed = indexer.fit(output).transform(output)
outputFixed.printSchema()
final_data = outputFixed.select('features','PrivateIndex')
train_data,test_data=final_data.randomSplit([0.75,0.25])
from pyspark.ml.classification import RandomForestClassifier,GBTClassifier, DecisionTreeClassifier
from pyspark.ml import Pipeline
dtc = DecisionTreeClassifier(labelCol='PrivateIndex', featuresCol='features')
rfc = RandomForestClassifier(numTrees=25,labelCol='PrivateIndex', featuresCol='features')
gbt = GBTClassifier(labelCol='PrivateIndex', featuresCol='features')
dtcModel = dtc.fit(train_data)
rfcModel = rfc.fit(train_data)
gbtModel = gbt.fit(train_data)
dtcPred = dtcModel.transform(test_data)
rfcPred = rfcModel.transform(test_data)
gbtPred = gbtModel.transform(test_data)
from pyspark.ml.evaluation import MulticlassClassificationEvaluator, BinaryClassificationEvaluator
binaryEval = BinaryClassificationEvaluator(labelCol='PrivateIndex')
multiEval = MulticlassClassificationEvaluator(metricName ='accuracy')
print('DTC Accuracy:')
binaryEval.evaluate(dtcPred)
print('RFC Accuracy:')
binaryEval.evaluate(rfcPred)
print('GBT Accuracy:')
binaryEval.evaluate(gbtPred)
cols = ['Apps',
'Accept',
'Enroll',
'Top10perc',
'Top25perc',
'F_Undergrad',
'P_Undergrad',
'Outstate',
'Room_Board',
'Books',
'Personal',
'PhD',
'Terminal',
'S_F_Ratio',
'perc_alumni',
'Expend',
'Grad_Rate']
for i,j in zip(cols,rfcModel.featureImportances):
print(i + '\t\t' + str(j))
gbtPred.printSchema()
binaryEval2 = BinaryClassificationEvaluator(labelCol='PrivateIndex', rawPredictionCol='prediction')
print('GBT Accuracy2:')
binaryEval2.evaluate(gbtPred)
from pyspark.ml.evaluation import MulticlassClassificationEvaluator