base commit

back.py

@@ -0,0 +1,25 @@
+from flask import Flask, request, render_template
+import os
+from werkzeug.datastructures import ImmutableMultiDict
+
+app = Flask(__name__)
+
+@app.route('/')
+def index():
+   return render_template("index.html")			#running the front end
+
+@app.route('/result',methods = ['POST'])		# when query is submitted in front end
+def result():
+	data = request.form  						# data is empty
+    											# need posted data here
+	imd = data.to_dict(flat=False)
+	print("answer=",imd['Query'][0])			#to convert the data type of the the query object generated to dict
+	ans = imd['Query'][0]
+	os.system("python test.py "+str(ans))
+	f = open("output.txt", "r")					#read the sparql query and return it on front end
+	line = f.read()
+	f.close()
+	return line
+
+if __name__ == '__main__':
+   app.run(debug = True)

data/1.cpp

@@ -0,0 +1,56 @@
+#include <bits/stdc++.h>
+
+using namespace std;
+
+typedef pair<int,int>   II;
+typedef vector< II >      VII;
+typedef vector<int>     VI;
+typedef vector<long long>     VLL;
+typedef vector< VI >    VVI;
+typedef long long int   LL;
+
+#define PB push_back
+#define MP make_pair
+#define F first
+#define S second
+#define SZ(a) (int)(a.size())
+#define ALL(a) a.begin(),a.end()
+#define SET(a,b) memset(a,b,sizeof(a))
+
+
+#define din(n) int n; scanf("%d",&n)
+#define dout(n) printf("%d\n",n)
+#define llin(n) long long n; scanf("%lld",&n)
+#define llout(n) printf("%lld\n",n)
+#define strin(s,l) char s[l]; scanf("%s",s)
+#define strout(n) printf("%s\n",n)
+#define fast_io ios_base::sync_with_stdio(false);cin.tie(NULL)
+#define endl '\n'
+
+#define TRACE
+
+#ifdef TRACE
+#define trace(...) __f(#__VA_ARGS__, __VA_ARGS__)
+template <typename Arg1>
+void __f(const char* name, Arg1&& arg1){
+        cerr << name << " : " << arg1 << '\n';
+}
+template <typename Arg1, typename... Args>
+void __f(const char* names, Arg1&& arg1, Args&&... args){
+        const char* comma = strchr(names + 1, ',');cerr.write(names, comma - names) << " : " << arg1<<" | ";__f(comma+1, args...);
+}
+#else
+#define trace(...)
+#endif
+bool cmpManh(const std::pair<long long,long long>& l, const std::pair<long long,long long>& r)  {
+return ((llabs(l.F) + llabs(l.S)) < (llabs(r.F) + llabs(r.S)));
+}
+
+int gcd(int a, int b){
+if (a == 0) return b; return gcd(b%a, a); 
+}
+
+int main(void)
+{
+    return(0);
+}

data/Compositions2/_model/best_bleu/checkpoint

@@ -0,0 +1,6 @@
+model_checkpoint_path: "translate.ckpt-7000"
+all_model_checkpoint_paths: "translate.ckpt-3000"
+all_model_checkpoint_paths: "translate.ckpt-4000"
+all_model_checkpoint_paths: "translate.ckpt-5000"
+all_model_checkpoint_paths: "translate.ckpt-6000"
+all_model_checkpoint_paths: "translate.ckpt-7000"

data/Compositions2/_model/best_bleu/hparams

@@ -0,0 +1 @@
+{"src": "en", "tgt": "sparql", "train_prefix": "../data/Compositions2//train", "dev_prefix": "../data/Compositions2//dev", "test_prefix": "../data/Compositions2//test", "vocab_prefix": "../data/Compositions2//vocab", "out_dir": "../data/Compositions2/_model", "num_units": 128, "num_layers": 2, "dropout": 0.2, "unit_type": "lstm", "encoder_type": "uni", "residual": false, "time_major": true, "num_embeddings_partitions": 0, "attention": "", "attention_architecture": "standard", "pass_hidden_state": true, "optimizer": "sgd", "num_train_steps": 10000, "batch_size": 128, "init_op": "uniform", "init_weight": 0.1, "max_gradient_norm": 5.0, "learning_rate": 1.0, "start_decay_step": 0, "decay_factor": 0.98, "decay_steps": 10000, "colocate_gradients_with_ops": true, "num_buckets": 5, "max_train": 0, "src_max_len": 50, "tgt_max_len": 50, "source_reverse": false, "src_max_len_infer": null, "tgt_max_len_infer": null, "infer_batch_size": 32, "beam_width": 0, "length_penalty_weight": 0.0, "sos": "<s>", "eos": "</s>", "bpe_delimiter": null, "forget_bias": 1.0, "num_gpus": 1, "epoch_step": 65, "steps_per_stats": 100, "steps_per_external_eval": null, "share_vocab": false, "metrics": ["bleu"], "log_device_placement": false, "random_seed": null, "num_residual_layers": 0, "src_vocab_size": 6165, "tgt_vocab_size": 6833, "src_vocab_file": "../data/Compositions2/_model/vocab.en", "tgt_vocab_file": "../data/Compositions2/_model/vocab.sparql", "best_bleu": 58.855024973094196, "best_bleu_dir": "../data/Compositions2/_model/best_bleu"}

data/Compositions2/_model/checkpoint

@@ -0,0 +1,6 @@
+model_checkpoint_path: "translate.ckpt-7000"
+all_model_checkpoint_paths: "translate.ckpt-3000"
+all_model_checkpoint_paths: "translate.ckpt-4000"
+all_model_checkpoint_paths: "translate.ckpt-5000"
+all_model_checkpoint_paths: "translate.ckpt-6000"
+all_model_checkpoint_paths: "translate.ckpt-7000"

data/Compositions2/_model/hparams

@@ -0,0 +1 @@
+{"src": "en", "tgt": "sparql", "train_prefix": "../data/Compositions2//train", "dev_prefix": "../data/Compositions2//dev", "test_prefix": "../data/Compositions2//test", "vocab_prefix": "../data/Compositions2//vocab", "out_dir": "../data/Compositions2/_model", "num_units": 128, "num_layers": 2, "dropout": 0.2, "unit_type": "lstm", "encoder_type": "uni", "residual": false, "time_major": true, "num_embeddings_partitions": 0, "attention": "", "attention_architecture": "standard", "pass_hidden_state": true, "optimizer": "sgd", "num_train_steps": 10000, "batch_size": 128, "init_op": "uniform", "init_weight": 0.1, "max_gradient_norm": 5.0, "learning_rate": 1.0, "start_decay_step": 0, "decay_factor": 0.98, "decay_steps": 10000, "colocate_gradients_with_ops": true, "num_buckets": 5, "max_train": 0, "src_max_len": 50, "tgt_max_len": 50, "source_reverse": false, "src_max_len_infer": null, "tgt_max_len_infer": null, "infer_batch_size": 32, "beam_width": 0, "length_penalty_weight": 0.0, "sos": "<s>", "eos": "</s>", "bpe_delimiter": null, "forget_bias": 1.0, "num_gpus": 1, "epoch_step": 0, "steps_per_stats": 100, "steps_per_external_eval": null, "share_vocab": false, "metrics": ["bleu"], "log_device_placement": false, "random_seed": null, "num_residual_layers": 0, "src_vocab_size": 6165, "tgt_vocab_size": 6833, "src_vocab_file": "../data/Compositions2/_model/vocab.en", "tgt_vocab_file": "../data/Compositions2/_model/vocab.sparql", "best_bleu": 64.80136634682646, "best_bleu_dir": "../data/Compositions2/_model/best_bleu"}

data/Compositions2/_model/log_1573854344

@@ -0,0 +1,14 @@
+# log_file=../data/Compositions2/_model/log_1573854344
+# Start step 0, lr 1, Sat Nov 16 03:15:46 2019
+  global step 100 lr 1 step-time 0.27s wps 8.71K ppl 21.31 bleu 0.00
+  global step 200 lr 1 step-time 0.27s wps 8.80K ppl 3.20 bleu 0.00
+  global step 300 lr 1 step-time 0.27s wps 8.82K ppl 2.94 bleu 0.00
+  global step 400 lr 1 step-time 0.29s wps 8.17K ppl 2.87 bleu 0.00
+  global step 500 lr 1 step-time 0.28s wps 8.48K ppl 2.84 bleu 0.00
+  global step 600 lr 1 step-time 0.29s wps 8.14K ppl 2.79 bleu 0.00
+  global step 700 lr 1 step-time 0.29s wps 8.37K ppl 2.74 bleu 0.00
+  global step 800 lr 1 step-time 0.29s wps 8.29K ppl 2.67 bleu 0.00
+  global step 900 lr 1 step-time 0.29s wps 8.17K ppl 2.56 bleu 0.00
+  global step 1000 lr 1 step-time 0.28s wps 8.45K ppl 2.46 bleu 0.00
+# Final, step 1000 lr 1 step-time 0.28 wps 8.45K ppl 2.46, dev ppl 2.53, dev bleu 58.9, test ppl 7.40, test bleu 63.4, Sat Nov 16 03:20:36 2019
+# Best bleu, step 1000 step-time 0.28 wps 8.45K, dev ppl 2.53, dev bleu 58.9, test ppl 7.40, test bleu 63.4, Sat Nov 16 03:20:39 2019

data/Compositions2/_model/log_1573854658

@@ -0,0 +1,60 @@
+# log_file=../data/Compositions2/_model/log_1573854658
+# Start step 1000, lr 1, Sat Nov 16 03:21:02 2019
+  global step 1100 lr 1 step-time 0.29s wps 8.72K ppl 2.29 bleu 58.86
+  global step 1200 lr 1 step-time 0.27s wps 8.64K ppl 2.28 bleu 58.86
+  global step 1300 lr 1 step-time 0.27s wps 8.81K ppl 2.25 bleu 58.86
+  global step 1400 lr 1 step-time 0.27s wps 8.80K ppl 2.14 bleu 58.86
+  global step 1500 lr 1 step-time 0.27s wps 8.76K ppl 2.11 bleu 58.86
+  global step 1600 lr 1 step-time 0.27s wps 8.78K ppl 2.11 bleu 58.86
+  global step 1700 lr 1 step-time 0.27s wps 8.71K ppl 2.05 bleu 58.86
+  global step 1800 lr 1 step-time 0.27s wps 8.78K ppl 2.01 bleu 58.86
+  global step 1900 lr 1 step-time 0.27s wps 8.74K ppl 1.99 bleu 58.86
+  global step 2000 lr 1 step-time 0.28s wps 8.68K ppl 1.98 bleu 58.86
+  global step 2100 lr 1 step-time 0.27s wps 8.79K ppl 1.94 bleu 61.84
+  global step 2200 lr 1 step-time 0.28s wps 8.56K ppl 1.93 bleu 61.84
+  global step 2300 lr 1 step-time 0.28s wps 8.50K ppl 1.90 bleu 61.84
+  global step 2400 lr 1 step-time 0.28s wps 8.61K ppl 1.88 bleu 61.84
+  global step 2500 lr 1 step-time 0.31s wps 7.61K ppl 1.86 bleu 61.84
+  global step 2600 lr 1 step-time 0.29s wps 8.24K ppl 1.85 bleu 61.84
+  global step 2700 lr 1 step-time 0.30s wps 7.99K ppl 1.83 bleu 61.84
+  global step 2800 lr 1 step-time 0.29s wps 8.31K ppl 1.82 bleu 61.84
+  global step 2900 lr 1 step-time 0.30s wps 7.92K ppl 1.79 bleu 61.84
+  global step 3000 lr 1 step-time 0.29s wps 8.19K ppl 1.78 bleu 61.84
+  global step 3100 lr 1 step-time 0.30s wps 8.11K ppl 1.77 bleu 63.27
+  global step 3200 lr 1 step-time 0.28s wps 8.64K ppl 1.76 bleu 63.27
+  global step 3300 lr 1 step-time 0.29s wps 8.34K ppl 1.75 bleu 63.27
+  global step 3400 lr 1 step-time 0.29s wps 8.20K ppl 1.73 bleu 63.27
+  global step 3500 lr 1 step-time 0.29s wps 8.20K ppl 1.72 bleu 63.27
+  global step 3600 lr 1 step-time 0.30s wps 7.96K ppl 1.71 bleu 63.27
+  global step 3700 lr 1 step-time 0.29s wps 8.39K ppl 1.70 bleu 63.27
+  global step 3800 lr 1 step-time 0.28s wps 8.57K ppl 1.69 bleu 63.27
+  global step 3900 lr 1 step-time 0.28s wps 8.56K ppl 1.68 bleu 63.27
+  global step 4000 lr 1 step-time 0.29s wps 8.16K ppl 1.82 bleu 63.27
+  global step 4100 lr 1 step-time 0.31s wps 7.79K ppl 1.67 bleu 63.45
+  global step 4200 lr 1 step-time 0.29s wps 8.33K ppl 1.66 bleu 63.45
+  global step 4300 lr 1 step-time 0.27s wps 8.74K ppl 1.65 bleu 63.45
+  global step 4400 lr 1 step-time 0.28s wps 8.42K ppl 1.64 bleu 63.45
+  global step 4500 lr 1 step-time 0.29s wps 8.15K ppl 1.65 bleu 63.45
+  global step 4600 lr 1 step-time 0.29s wps 8.16K ppl 1.63 bleu 63.45
+  global step 4700 lr 1 step-time 0.28s wps 8.67K ppl 1.62 bleu 63.45
+  global step 4800 lr 1 step-time 0.28s wps 8.58K ppl 1.62 bleu 63.45
+  global step 4900 lr 1 step-time 0.28s wps 8.65K ppl 1.62 bleu 63.45
+  global step 5000 lr 1 step-time 0.28s wps 8.61K ppl 1.61 bleu 63.45
+  global step 5100 lr 1 step-time 0.28s wps 8.44K ppl 1.60 bleu 63.82
+  global step 5200 lr 1 step-time 0.28s wps 8.40K ppl 1.59 bleu 63.82
+  global step 5300 lr 1 step-time 0.28s wps 8.61K ppl 1.59 bleu 63.82
+  global step 5400 lr 1 step-time 0.28s wps 8.48K ppl 1.58 bleu 63.82
+  global step 5500 lr 1 step-time 0.29s wps 8.39K ppl 1.58 bleu 63.82
+  global step 5600 lr 1 step-time 0.28s wps 8.55K ppl 1.58 bleu 63.82
+  global step 5700 lr 1 step-time 0.28s wps 8.36K ppl 1.57 bleu 63.82
+  global step 5800 lr 1 step-time 0.30s wps 8.03K ppl 1.56 bleu 63.82
+  global step 5900 lr 1 step-time 0.29s wps 8.27K ppl 1.56 bleu 63.82
+  global step 6000 lr 1 step-time 0.29s wps 8.31K ppl 1.56 bleu 63.82
+  global step 6100 lr 1 step-time 0.28s wps 8.62K ppl 1.55 bleu 64.33
+  global step 6200 lr 1 step-time 0.28s wps 8.67K ppl 1.55 bleu 64.33
+  global step 6300 lr 1 step-time 0.28s wps 8.47K ppl 1.54 bleu 64.33
+  global step 6400 lr 1 step-time 0.28s wps 8.44K ppl 1.53 bleu 64.33
+  global step 6500 lr 1 step-time 0.28s wps 8.51K ppl 1.53 bleu 64.33
+  global step 6600 lr 1 step-time 0.28s wps 8.51K ppl 1.52 bleu 64.33
+  global step 6700 lr 1 step-time 0.29s wps 8.10K ppl 1.51 bleu 64.33
+