added essay evaluator

Softlab.yml

+name: Softlab
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - ca-certificates=2019.10.16=0
+  - certifi=2019.9.11=py37_0
+  - libedit=3.1.20181209=hc058e9b_0
+  - libffi=3.2.1=hd88cf55_4
+  - libgcc-ng=9.1.0=hdf63c60_0
+  - libstdcxx-ng=9.1.0=hdf63c60_0
+  - ncurses=6.1=he6710b0_1
+  - openssl=1.1.1d=h7b6447c_3
+  - pip=19.3.1=py37_0
+  - python=3.7.4=h265db76_1
+  - readline=7.0=h7b6447c_5
+  - setuptools=41.4.0=py37_0
+  - sqlite=3.30.1=h7b6447c_0
+  - tk=8.6.8=hbc83047_0
+  - wheel=0.33.6=py37_0
+  - xz=5.2.4=h14c3975_4
+  - zlib=1.2.11=h7b6447c_3
+  - pip:
+    - absl-py==0.8.1
+    - astor==0.8.0
+    - boto==2.49.0
+    - boto3==1.10.4
+    - botocore==1.13.4
+    - chardet==3.0.4
+    - docutils==0.15.2
+    - gast==0.2.2
+    - gensim==3.8.1
+    - google-pasta==0.1.7
+    - grpcio==1.24.3
+    - h5py==2.10.0
+    - idna==2.8
+    - jmespath==0.9.4
+    - keras-applications==1.0.8
+    - keras-preprocessing==1.1.0
+    - markdown==3.1.1
+    - nltk==3.4.5
+    - numpy==1.17.3
+    - opt-einsum==3.1.0
+    - protobuf==3.10.0
+    - python-dateutil==2.8.0
+    - requests==2.22.0
+    - s3transfer==0.2.1
+    - scipy==1.3.1
+    - six==1.12.0
+    - smart-open==1.8.4
+    - tensorboard==2.0.0
+    - tensorflow==2.0.0
+    - tensorflow-estimator==2.0.1
+    - termcolor==1.1.0
+    - urllib3==1.25.6
+    - werkzeug==0.16.0
+    - wrapt==1.11.2
+prefix: /home/shreyansh/.conda/envs/Softlab
+

main.js

@@ -27,7 +27,28 @@ app.get('/', (req, res) => {
 });
 
 app.post('/evaluate', (req, res) => {
-    res.send('Hello world\n');
+    var essay = req.body.essay;
+    new Promise(function(resolve, reject) {
+
+        const { spawn } = require('child_process');
+        const predict = spawn('python3',['prediction.py',essay]);
+    
+        predict.stdout.on('data', function(data) {
+            data = new Buffer.from(data, 'base64').toString("ascii")
+            resolve(data);
+        });
+    
+        predict.stderr.on('data', (data) => {
+            data = new Buffer.from(data, 'base64').toString("ascii")
+            reject(data);
+        });
+    })
+    .then((marks)=>{
+        res.send(marks)
+    })
+    .catch((err)=>{
+        console.log(err)
+    })
 });
 
 

package.json

@@ -9,7 +9,8 @@
   },
   "dependencies": {
     "express": "^4.16.1",
-    "request": "^2.88.0",
-    "googleapis": "^44.0.0"
+    "googleapis": "^44.0.0",
+    "plagiarism-checker": "^1.2.1",
+    "request": "^2.88.0"
   }
 }

plagarismCheck.js

+var request = require('request');
+var CopyleaksCloud = require('plagiarism-checker');
+var _ = require('lodash');
+var clCloud = new CopyleaksCloud();
+var config = clCloud.getConfig();
+
+var credentials = {
+    "Email": "sjain0615@gmail.com",
+    "ApiKey": "89893811-8da7-432b-8f40-7d4eb6456693"
+}
+
+let access_token;
+
+var essay = 'yes i am on moonlight. yes i am on moonlight yes .i am on moonlight yes i am on moonlightyes i am on moonlight. yes i am on moonlight. yes i am on moonlight';
+
+clCloud.login(credentials.Email,credentials.ApiKey,'education',function(resp,err){
+    if(!err){
+        access_token = _.get(resp,'access_token','');
+        console.log(resp);
+        var _customHeaders = {};
+        _customHeaders[config.SANDBOX_MODE_HEADER] = true; // Sandbox mode - Scan without consuming any credits and get back dummy results
+        _customHeaders[config.HTTP_CALLBACK] = 'http://requestb.in/callbacks/' // Callback url - For a fast testing of callbacks option we recommend to use http://requestb.in
+        
+        clCloud.createByText(essay,_customHeaders,function(resp,err){
+            console.log(resp)
+            if(resp && resp.ProcessId){
+                let PID = resp.ProcessId
+                let Status = 'Processing'
+                clCloud.getProcessStatus(PID,function(resp,err){
+                    console.log(resp.Status,resp)
+                    if(resp.Status==='Finished'){
+                        clCloud.getProcessResults(PID,function(resp,err){
+                        console.log(resp);
+                        setTimeout(function(){
+                            })
+                        },15);
+
+
+                    }
+                    else{
+                        clCloud.getProcessResults(PID,function(resp,err){
+                        console.log(resp.results);
+                        setTimeout(function(){
+
+                        },15);
+                        })
+                    }
+                })
+            }
+        }); 
+    }
+})
+
+// var pid = '4decf855-60d6-4b9e-985b-4bfcfdb6bd63'
+
+
+// function setToken(){
+
+//     var headers = {
+//         "Content-type": "application/json"
+//     };
+    
+
+    
+//     var options = {
+//         url: "https://id.copyleaks.com/v1/account/login-api",
+//         method: "POST",
+//         headers: headers,
+//         body: dataString,
+//         json: true
+//     };
+    
+//     return new Promise(function(resolve,reject){
+//         clCloud.login(options, function(error, response, body) {
+//             if (!error && response.statusCode == 200)
+//                 resolve(body.access_token)
+//             else
+//                 reject(error)
+//         })
+//     })
+// }
+
+// function scanFile(token, essay){
+
+//     var headers = {
+//         'Authorization': `Bearer ${token}`,
+//         'Content-type': "application/json"
+//     };
+
+    
+//     var options = {
+//         url: "https://id.copyleaks.com/v2/education/4d7728fb-ed3e-4c77-8a2c-07783cfad046/result",
+//         method: "GET",
+//         headers: headers,
+//         body: essay
+//     };
+
+//     request(options,function(error, response, body) {
+//         if (!error && response.statusCode == 200) {
+//             console.log(body);
+//         }
+//     });
+// }
+
+// setToken()
+// .then((token)=>{
+//     scanFile(token,essay)
+// })
+// .catch((err)=>console.log('err '+err))

prediction.py

+import os
+import re
+import sys
+import nltk
+import warnings
+import numpy as np
+from tensorflow import keras
+from nltk.corpus import stopwords
+from gensim.models import KeyedVectors
+# nltk.download('stopwords')
+warnings.filterwarnings("ignore")
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
+
+def tokenizeEssay(essay):
+    """ Adding everything except stopwords to wordsList"""
+    essay = re.sub("[^a-zA-Z]", " ", essay)
+    words = essay.lower().split()
+    stops = set(stopwords.words("english"))
+    words = [w for w in words if not w in stops]
+    return (words)
+
+def makeFeatureVec(words, model, num_features):
+    """Make Feature Vector from the words list of an Essay."""
+    featureVec = np.zeros((num_features,),dtype="float32")
+    num_words = 0.
+    index2word_set = set(model.index2word)
+    for word in words:
+        if word in index2word_set:
+            num_words += 1
+            featureVec = np.add(featureVec,model[word])        
+    featureVec = np.divide(featureVec,num_words)
+    return featureVec
+
+def getAvgFeatureVecs(essays, model, num_features):
+    """Main function to generate the word vectors for word2vec model."""
+    counter = 0
+    essayFeatureVecs = np.zeros((len(essays),num_features),dtype="float32")
+    for essay in essays:
+        essayFeatureVecs[counter] = makeFeatureVec(essay, model, num_features)
+        counter = counter + 1
+    return essayFeatureVecs
+
+
+model = KeyedVectors.load_word2vec_format('models/word2vecmodel.bin', binary=True)
+essay_tokens = []
+essay = sys.argv[1]
+
+essay_tokens.append(tokenizeEssay(essay))
+testEssayVec = getAvgFeatureVecs(essay_tokens, model, 300)
+
+testEssayVec = np.array(testEssayVec)
+testEssayVec = np.reshape(testEssayVec,(testEssayVec.shape[0], 1, testEssayVec.shape[1]))
+
+evaluator = keras.models.load_model('models/final_lstm.h5')
+y_pred = evaluator.predict(testEssayVec)
+y_pred = np.around(y_pred)
+print(y_pred.reshape(-1)[0])
\ No newline at end of file