Random Forest Classifier accuracy doesn't get higher than 50%
-2
I am very new to machine learning and I am trying to classify this UCI Heart Disease Dataset using sklearn's random forest classifier. My approach is very basic, and I wanted to ask how I could improve my accuracy with the algorithm (some tips, links, etc.). My accuracy tops out at about 50% every time. Here's my code:
import pandas as pd
import numpy as np
import random as random
import sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
df = pd.read_excel('/Users/Mady/Documents/ClevelandData.xlsx')
df.replace('?', -99999, inplace=True)
labels = df.iloc[:,-1]
labels = labels.values
df.drop(df.columns[len(df.columns)-1], axis=1, inplace=True)
riskFactors = df.values
random.seed(123)
random.shuffle(labels)
random.seed(123)
random.shuffle(riskFactors)
labels_train = labels[:(int(len(labels) * 0.8))]
labels_test = labels[(int(len(labels) * 0.8)):]
riskFactors_train = riskFactors[:(int(len(riskFactors) * 0.8))]
riskFactors_test = riskFactors[(int(len(riskFactors) * 0.8)):]
model = RandomForestClassifier(n_estimators = 1000)
model.fit(riskFactors_train,labels_train)
predicted_labels = model.predict(riskFactors_test)
acc = accuracy_score(labels_test,predicted_labels)
print(acc)
python machine-learning scikit-learn random-forest
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
add a comment |
-2
I am very new to machine learning and I am trying to classify this UCI Heart Disease Dataset using sklearn's random forest classifier. My approach is very basic, and I wanted to ask how I could improve my accuracy with the algorithm (some tips, links, etc.). My accuracy tops out at about 50% every time. Here's my code:
import pandas as pd
import numpy as np
import random as random
import sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
df = pd.read_excel('/Users/Mady/Documents/ClevelandData.xlsx')
df.replace('?', -99999, inplace=True)
labels = df.iloc[:,-1]
labels = labels.values
df.drop(df.columns[len(df.columns)-1], axis=1, inplace=True)
riskFactors = df.values
random.seed(123)
random.shuffle(labels)
random.seed(123)
random.shuffle(riskFactors)
labels_train = labels[:(int(len(labels) * 0.8))]
labels_test = labels[(int(len(labels) * 0.8)):]
riskFactors_train = riskFactors[:(int(len(riskFactors) * 0.8))]
riskFactors_test = riskFactors[(int(len(riskFactors) * 0.8)):]
model = RandomForestClassifier(n_estimators = 1000)
model.fit(riskFactors_train,labels_train)
predicted_labels = model.predict(riskFactors_test)
acc = accuracy_score(labels_test,predicted_labels)
print(acc)
python machine-learning scikit-learn random-forest
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
2
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use thetrain_test_splitprovided by sklearn.
– Yilun Zhang
Nov 12 '18 at 19:38
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14
add a comment |
-2
-2
-2
I am very new to machine learning and I am trying to classify this UCI Heart Disease Dataset using sklearn's random forest classifier. My approach is very basic, and I wanted to ask how I could improve my accuracy with the algorithm (some tips, links, etc.). My accuracy tops out at about 50% every time. Here's my code:
import pandas as pd
import numpy as np
import random as random
import sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
df = pd.read_excel('/Users/Mady/Documents/ClevelandData.xlsx')
df.replace('?', -99999, inplace=True)
labels = df.iloc[:,-1]
labels = labels.values
df.drop(df.columns[len(df.columns)-1], axis=1, inplace=True)
riskFactors = df.values
random.seed(123)
random.shuffle(labels)
random.seed(123)
random.shuffle(riskFactors)
labels_train = labels[:(int(len(labels) * 0.8))]
labels_test = labels[(int(len(labels) * 0.8)):]
riskFactors_train = riskFactors[:(int(len(riskFactors) * 0.8))]
riskFactors_test = riskFactors[(int(len(riskFactors) * 0.8)):]
model = RandomForestClassifier(n_estimators = 1000)
model.fit(riskFactors_train,labels_train)
predicted_labels = model.predict(riskFactors_test)
acc = accuracy_score(labels_test,predicted_labels)
print(acc)
python machine-learning scikit-learn random-forest
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
I am very new to machine learning and I am trying to classify this UCI Heart Disease Dataset using sklearn's random forest classifier. My approach is very basic, and I wanted to ask how I could improve my accuracy with the algorithm (some tips, links, etc.). My accuracy tops out at about 50% every time. Here's my code:
import pandas as pd
import numpy as np
import random as random
import sklearn
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
df = pd.read_excel('/Users/Mady/Documents/ClevelandData.xlsx')
df.replace('?', -99999, inplace=True)
labels = df.iloc[:,-1]
labels = labels.values
df.drop(df.columns[len(df.columns)-1], axis=1, inplace=True)
riskFactors = df.values
random.seed(123)
random.shuffle(labels)
random.seed(123)
random.shuffle(riskFactors)
labels_train = labels[:(int(len(labels) * 0.8))]
labels_test = labels[(int(len(labels) * 0.8)):]
riskFactors_train = riskFactors[:(int(len(riskFactors) * 0.8))]
riskFactors_test = riskFactors[(int(len(riskFactors) * 0.8)):]
model = RandomForestClassifier(n_estimators = 1000)
model.fit(riskFactors_train,labels_train)
predicted_labels = model.predict(riskFactors_test)
acc = accuracy_score(labels_test,predicted_labels)
print(acc)
python machine-learning scikit-learn random-forest
python machine-learning scikit-learn random-forest
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
asked Nov 12 '18 at 19:08
Kasy ChakraKasy Chakra
85
85
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
2
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use thetrain_test_splitprovided by sklearn.
– Yilun Zhang
Nov 12 '18 at 19:38
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14
add a comment |
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
2
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use thetrain_test_splitprovided by sklearn.
– Yilun Zhang
Nov 12 '18 at 19:38
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
2
2
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use the
train_test_split provided by sklearn.– Yilun Zhang
Nov 12 '18 at 19:38
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use the
train_test_split provided by sklearn.– Yilun Zhang
Nov 12 '18 at 19:38
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14
add a comment |
1 Answer
1
active
oldest
votes
0
Solved this by removing the random part as there must have been some error there.
As suggested by Yulin Zhang, I used the train_test_split provided by sklearn.
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53268587%2frandom-forest-classifier-accuracy-doesnt-get-higher-than-50%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
0
Solved this by removing the random part as there must have been some error there.
As suggested by Yulin Zhang, I used the train_test_split provided by sklearn.
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
add a comment |
0
Solved this by removing the random part as there must have been some error there.
As suggested by Yulin Zhang, I used the train_test_split provided by sklearn.
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
add a comment |
0
0
0
Solved this by removing the random part as there must have been some error there.
As suggested by Yulin Zhang, I used the train_test_split provided by sklearn.
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
Solved this by removing the random part as there must have been some error there.
As suggested by Yulin Zhang, I used the train_test_split provided by sklearn.
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
answered Dec 5 '18 at 3:06
Kasy ChakraKasy Chakra
85
85
add a comment |
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
draft saved
draft discarded
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53268587%2frandom-forest-classifier-accuracy-doesnt-get-higher-than-50%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
explore your data first. look for patterns that you think your model should be able to estimate. what makes you think your dataset is estimable beyond a 50% accuracy rate?
– John H
Nov 12 '18 at 19:12
Hi, welcome to StackOverflow. This question may be too broad for this forum. I suggest posting to Code Review or Data Science. datascience.stackexchange.com
– Evan
Nov 12 '18 at 19:14
There is some principal trouble with you data or labels. Could you please provide some sample from the date and label?
– Geeocode
Nov 12 '18 at 19:24
2
I think you messed up when you are shuffling the labels and riskFactors, for consistency, you should try to use the
train_test_splitprovided by sklearn.– Yilun Zhang
Nov 12 '18 at 19:38
Thank you so much! I am definitely a newbie to this as I got to 80% simply by using the train_test_split and removing the random part(there must have been some error there).
– Kasy Chakra
Nov 12 '18 at 20:14