Add files via upload

Author: showman-sharma

__pycache__/chatbot.cpython-310.pyc

@@ -0,0 +1,5 @@
+Here's our complete catalogue:
+MARK I: For arm amputees. Our simple and light weight model of arm prosthesis. Suitable for simple tasks.
+MARK II: For arm amputees. An advanced and dextrous arm. Involves softroboric for best grip and individual finger control.
+EXO 0: For hand injury rehabilitation and hand paralysis. Comfortable, light-weight and simple.
+EXO I: For hand injury rehabilitation and hand paralysis. Dextrous movements and powerful gripping action.

__pycache__/customeVectorizor.cpython-310.pyc

@@ -0,0 +1,3 @@
+Prosthesis is a very personalized solution, differening from user to user. 
+Kindly provide your details here and we will contact you:
+https://forms.gle/C6Em8mSkH5zgbS576

bot_label_encoder.npy

@@ -0,0 +1,2 @@
+Handyman Prosthetics create hand prosthesis and exoskeleton support for people who lost their arms or the ability to control it.
+Our perosonalized solutions enable them to carry out simple day to day tasks without having to rely on others. 

bot_replies/all_products.txt

@@ -0,0 +1,2 @@
+Sure! Here's a video demo: 
+https://youtube.com/playlist?list=PLsE-jsMAf6MONnhrq0_Z4-rIY8xSVyArC

bot_replies/buy_request.txt

@@ -0,0 +1 @@
+Thank you for contacting us. Have a nice day!

bot_replies/company_info.txt

@@ -0,0 +1,3 @@
+Here are our exoskeleton support solutions:
+EXO 0: For hand injury rehabilitation and hand paralysis. Comfortable, light-weight and simple.
+EXO I: For hand injury rehabilitation and hand paralysis. Dextrous movements and powerful gripping action.

bot_replies/demo_request.txt

@@ -0,0 +1,3 @@
+Here are our arm prosthesis solutions:
+MARK I: For arm amputees. Our simple and light weight model of arm prosthesis. Suitable for simple tasks.
+MARK II: For arm amputees. An advanced and dextrous arm. Involves softroboric for best grip and individual finger control.

bot_replies/end_convo.txt

@@ -0,0 +1 @@
+Hi! I am Handy, AI chatbot of Handyman Prosthetics. How may I help you?

bot_replies/exoskeleton_product.txt

@@ -0,0 +1,64 @@
+from sklearn import preprocessing
+import numpy as np
+import pickle
+from tensorflow import keras
+
+
+
+class chatbot:
+    def __init__(self):
+
+        #Loading a Model 
+        self.loaded_model = keras.models.load_model("chatbot_model");
+
+        #Print Model Summary
+        # self.loaded_model.summary()
+
+        #Convert input into IF-IDF vector using the same vectorizer model
+        self.vectorizer = pickle.load( open( "bot_vectorizer.p", "rb" ) );
+
+        self.encoder = preprocessing.LabelEncoder();
+        self.encoder.classes_ = np.load('bot_label_encoder.npy',allow_pickle=True);
+
+
+        self.start_state = 'start_convo'
+        self.end_state = 'end_convo'
+
+        #Loading Bot Replies
+        bot_reply_classes = [self.start_state]+list(self.encoder.classes_) 
+        self.bot_replies = {}
+        for reply_class in bot_reply_classes:
+            with open('bot_replies/'+reply_class+'.txt') as f:
+                self.bot_replies[reply_class] = f.readlines()
+
+    def respond(self,user_reply):
+        if user_reply==None or len(user_reply)<=3:
+            state = self.start_state
+            print("\n\n")
+        else:
+            predict_tfidf=self.vectorizer.transform([user_reply]).toarray();
+            prediction=np.argmax( self.loaded_model.predict(predict_tfidf), axis=1 );  
+            state = self.encoder.inverse_transform(prediction)[0]
+        convo = True
+        if state == self.end_state:
+            convo = False
+                
+        return self.bot_replies[state], convo      
+
+
+
+
+
+# state = start_state
+# while state!=end_state:
+#     for line in bot_replies[state]:
+#         print('Handy: '+line.strip())
+        
+#     user_reply = input('user: ')
+    
+#     predict_tfidf=vectorizer.transform([user_reply]).toarray();
+#     prediction=np.argmax( loaded_model.predict(predict_tfidf), axis=1 );
+    
+#     state = encoder.inverse_transform(prediction)[0]
+# for line in bot_replies[state]:
+#     print('Handy: '+line.strip())

bot_replies/prosthesis_products.txt

@@ -0,0 +1,8 @@
+
+�.root"_tf_keras_sequential*�-{"name": "sequential_1", "trainable": true, "expects_training_arg": true, "dtype": "float32", "batch_input_shape": null, "must_restore_from_config": false, "class_name": "Sequential", "config": {"name": "sequential_1", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "Hidden-Layer-1_input"}}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-2", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-3", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}, {"class_name": "Dense", "config": {"name": "Output-Layer", "trainable": true, "dtype": "float32", "units": 7, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}}]}, "shared_object_id": 13, "input_spec": [{"class_name": "InputSpec", "config": {"dtype": null, "shape": {"class_name": "__tuple__", "items": [null, 73]}, "ndim": 2, "max_ndim": null, "min_ndim": null, "axes": {}}}], "build_input_shape": {"class_name": "TensorShape", "items": [null, 73]}, "is_graph_network": true, "full_save_spec": {"class_name": "__tuple__", "items": [[{"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, 73]}, "float32", "Hidden-Layer-1_input"]}], {}]}, "save_spec": {"class_name": "TypeSpec", "type_spec": "tf.TensorSpec", "serialized": [{"class_name": "TensorShape", "items": [null, 73]}, "float32", "Hidden-Layer-1_input"]}, "keras_version": "2.9.0", "backend": "tensorflow", "model_config": {"class_name": "Sequential", "config": {"name": "sequential_1", "layers": [{"class_name": "InputLayer", "config": {"batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "dtype": "float32", "sparse": false, "ragged": false, "name": "Hidden-Layer-1_input"}, "shared_object_id": 0}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 1}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 2}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 3}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-2", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 4}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 5}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 6}, {"class_name": "Dense", "config": {"name": "Hidden-Layer-3", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 7}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 8}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 9}, {"class_name": "Dense", "config": {"name": "Output-Layer", "trainable": true, "dtype": "float32", "units": 7, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 10}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 11}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 12}]}}, "training_config": {"loss": "categorical_crossentropy", "metrics": [[{"class_name": "MeanMetricWrapper", "config": {"name": "accuracy", "dtype": "float32", "fn": "categorical_accuracy"}, "shared_object_id": 15}]], "weighted_metrics": null, "loss_weights": null, "optimizer_config": {"class_name": "RMSprop", "config": {"name": "RMSprop", "learning_rate": 0.0010000000474974513, "decay": 0.0, "rho": 0.8999999761581421, "momentum": 0.0, "epsilon": 1e-07, "centered": false}}}}2

+�
root.layer_with_weights-0"_tf_keras_layer*�{"name": "Hidden-Layer-1", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "Hidden-Layer-1", "trainable": true, "batch_input_shape": {"class_name": "__tuple__", "items": [null, 73]}, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 1}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 2}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 3, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 73}}, "shared_object_id": 16}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 73]}}2

+�root.layer_with_weights-1"_tf_keras_layer*�{"name": "Hidden-Layer-2", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "Hidden-Layer-2", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 4}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 5}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 6, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 32}}, "shared_object_id": 17}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 32]}}2

+�root.layer_with_weights-2"_tf_keras_layer*�{"name": "Hidden-Layer-3", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "Hidden-Layer-3", "trainable": true, "dtype": "float32", "units": 32, "activation": "relu", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 7}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 8}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 9, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 32}}, "shared_object_id": 18}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 32]}}2

+�root.layer_with_weights-3"_tf_keras_layer*�{"name": "Output-Layer", "trainable": true, "expects_training_arg": false, "dtype": "float32", "batch_input_shape": null, "stateful": false, "must_restore_from_config": false, "class_name": "Dense", "config": {"name": "Output-Layer", "trainable": true, "dtype": "float32", "units": 7, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "GlorotUniform", "config": {"seed": null}, "shared_object_id": 10}, "bias_initializer": {"class_name": "Zeros", "config": {}, "shared_object_id": 11}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "shared_object_id": 12, "input_spec": {"class_name": "InputSpec", "config": {"dtype": null, "shape": null, "ndim": null, "max_ndim": null, "min_ndim": 2, "axes": {"-1": 32}}, "shared_object_id": 19}, "build_input_shape": {"class_name": "TensorShape", "items": [null, 32]}}2

+�
]root.keras_api.metrics.0"_tf_keras_metric*�
{"class_name": "Mean", "name": "loss", "dtype": "float32", "config": {"name": "loss", "dtype": "float32"}, "shared_object_id": 20}2

+�
^root.keras_api.metrics.1"_tf_keras_metric*�
{"class_name": "MeanMetricWrapper", "name": "accuracy", "dtype": "float32", "config": {"name": "accuracy", "dtype": "float32", "fn": "categorical_accuracy"}, "shared_object_id": 15}2

bot_replies/start_convo.txt

@@ -0,0 +1,29 @@
+import nltk
+from nltk.stem import WordNetLemmatizer
+from nltk.corpus import stopwords
+from sklearn import preprocessing
+import numpy as np
+
+
+
+from sklearn.feature_extraction.text import TfidfVectorizer
+
+#Build a TF-IDF Vectorizer model
+
+#Custom tokenizer to remove stopwords and use lemmatization
+lemmatizer = WordNetLemmatizer()
+def customtokenize(str):
+            #Split string as tokens
+            tokens=nltk.word_tokenize(str)
+            #Filter for stopwords
+            nostop = list(filter(lambda token: token not in stopwords.words('english'), tokens))
+            #Perform lemmatization
+            
+            lemmatized=[lemmatizer.lemmatize(word) for word in nostop ]
+            return lemmatized
+
+# vectorizer = TfidfVectorizer(tokenizer=customtokenize)
+
+class customVect(TfidfVectorizer):
+    def __init__():
+        customVect.tokenizer = customtokenize;

bot_vectorizer.p

@@ -0,0 +1,34 @@
+
+import chatbot
+from nltk.stem import WordNetLemmatizer
+from nltk.corpus import stopwords
+import nltk
+
+lemmatizer = WordNetLemmatizer()
+def customtokenize(str):
+    #Split string as tokens
+    tokens=nltk.word_tokenize(str)
+    #Filter for stopwords
+    nostop = list(filter(lambda token: token not in stopwords.words('english'), tokens))
+    #Perform lemmatization
+    lemmatized=[lemmatizer.lemmatize(word) for word in nostop ]
+    return lemmatized
+
+
+import sys
+if __name__ == '__main__':
+
+    try:
+
+        user_reply = " ".join(sys.argv[1:])
+        print("User: "+user_reply)
+    except:
+        user_reply = None
+    chatbot = chatbot.chatbot()
+    bot_reply, convo = chatbot.respond(user_reply)
+    print(convo)
+    for line in bot_reply:
+        print('Handy: '+line.strip())
+
+
+

chatbot.py

@@ -0,0 +1,2 @@
+print('hellow')
+print('mellow')

chatbot_model/keras_metadata.pb

@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="JAVA_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$">
+      <sourceFolder url="file://$MODULE_DIR$/src" isTestSource="false" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+    <orderEntry type="library" name="jython-standalone-2.7.2" level="project" />
+  </component>
+</module>