first commit ours

app.py

@@ -0,0 +1,185 @@
+import os
+import pprint
+import tempfile
+from typing import Dict, Text
+import numpy as np
+import tensorflow as tf
+import tensorflow_recommenders as tfrs
+import os
+import unidecode
+from nltk import word_tokenize
+import re
+import pandas as pd
+from nltk.util import ngrams
+import base64
+import hashlib
+import gradio as gr
+import scann
+
+df=pd.read_csv("/home/user/app/Qatar_translated_best_2500.csv",sep=",",header=0)
+df=df.drop_duplicates()
+df=df.dropna()
+df["nome_vaga"]=df["nome_vaga"].map(lambda x: x.lower().title())
+df["requisito"]=df["requisito"].map(lambda x: x[0:1000].lower())
+my_dict=dict(df.iloc[0:int(df.shape[0]*0.9),:])
+my_dict_cego=dict(df.iloc[int(df.shape[0]*0.9):,:])
+ratings = tf.data.Dataset.from_tensor_slices(my_dict).map(lambda x: {
+    "code": x["code"],
+    "nome_vaga": x["nome_vaga"],
+    "requisito": tf.strings.split(x["requisito"],maxsplit=106)
+})
+movies = tf.data.Dataset.from_tensor_slices(dict(df)).map(lambda x: {
+    "code": x["code"],
+    "nome_vaga": x["nome_vaga"]
+})
+movies = movies.map(lambda x: x["code"])
+ratings_cego = tf.data.Dataset.from_tensor_slices(my_dict_cego).map(lambda x: {
+    "code": x["code"],
+    "requisito": tf.strings.split(x["requisito"],maxsplit=106)
+})
+tf.random.set_seed(42)
+shuffled = ratings.shuffle(int(df.shape[0]*0.9), seed=42, reshuffle_each_iteration=False)
+shuffled2 = ratings_cego.shuffle(int(df.shape[0]*0.1), seed=42, reshuffle_each_iteration=False)
+train = shuffled.take(int(df.shape[0]*0.9))
+test = shuffled.take(int(df.shape[0]*0.1))
+cego=shuffled2
+movie_titles = movies#.map(lambda x: x["code"])
+user_ids = ratings.map(lambda x: x["requisito"])
+xx=[]
+for x in user_ids.as_numpy_iterator():
+    try:
+        xx.append(x)
+    except:
+        pass
+unique_movie_titles = np.unique(list(movie_titles.as_numpy_iterator()))
+unique_user_ids = np.unique(np.concatenate(xx))
+user_ids=user_ids.batch(int(df.shape[0]*0.9))
+layer = tf.keras.layers.StringLookup(vocabulary=unique_user_ids)
+unique_movie_titles[:10]
+embedding_dimension = 768
+user_model = tf.keras.Sequential([
+  tf.keras.layers.StringLookup(
+      vocabulary=unique_user_ids, mask_token=None),
+  # We add an additional embedding to account for unknown tokens.
+  tf.keras.layers.Embedding(len(unique_user_ids) + 1, embedding_dimension),
+  
+])
+movie_model = tf.keras.Sequential([
+  tf.keras.layers.StringLookup(
+      vocabulary=unique_movie_titles, mask_token=None),
+  tf.keras.layers.Embedding(len(unique_movie_titles) + 1, embedding_dimension)
+])
+metrics = tfrs.metrics.FactorizedTopK(
+  candidates=movies.batch(df.shape[0]
+).map(movie_model)
+)
+task = tfrs.tasks.Retrieval(
+  metrics=metrics
+)
+class MovielensModel(tfrs.Model):
+
+  def __init__(self, user_model, movie_model):
+    super().__init__()
+    self.movie_model: tf.keras.Model = movie_model
+    self.user_model: tf.keras.Model = user_model
+    self.task: tf.keras.layers.Layer = task
+
+  def compute_loss(self, features: Dict[Text, tf.Tensor], training=False) -> tf.Tensor:
+    user_embeddings = self.user_model(features["requisito"])
+    positive_movie_embeddings = self.movie_model(features["code"])
+    return self.task(tf.reduce_sum(user_embeddings,axis=1), positive_movie_embeddings)
+
+class NoBaseClassMovielensModel(tf.keras.Model):
+
+  def __init__(self, user_model, movie_model):
+    super().__init__()
+    self.movie_model: tf.keras.Model = movie_model
+    self.user_model: tf.keras.Model = user_model
+    self.task: tf.keras.layers.Layer = task
+
+  def train_step(self, features: Dict[Text, tf.Tensor]) -> tf.Tensor:
+
+    with tf.GradientTape() as tape:
+
+      user_embeddings = self.user_model(features["requisito"])
+      positive_movie_embeddings = self.movie_model(features["code"])
+      loss = self.task(user_embeddings, positive_movie_embeddings)
+
+      regularization_loss = sum(self.losses)
+
+      total_loss = loss + regularization_loss
+
+    gradients = tape.gradient(total_loss, self.trainable_variables)
+    self.optimizer.apply_gradients(zip(gradients, self.trainable_variables))
+
+    metrics = {metric.name: metric.result() for metric in self.metrics}
+    metrics["loss"] = loss
+    metrics["regularization_loss"] = regularization_loss
+    metrics["total_loss"] = total_loss
+
+    return metrics
+
+  def test_step(self, features: Dict[Text, tf.Tensor]) -> tf.Tensor:
+
+    user_embeddings = self.user_model(features["requisito"])
+    positive_movie_embeddings = self.movie_model(features["code"])
+    loss = self.task(user_embeddings, positive_movie_embeddings)
+
+    regularization_loss = sum(self.losses)
+
+    total_loss = loss + regularization_loss
+
+    metrics = {metric.name: metric.result() for metric in self.metrics}
+    metrics["loss"] = loss
+    metrics["regularization_loss"] = regularization_loss
+    metrics["total_loss"] = total_loss
+
+    return metrics
+
+model = MovielensModel(user_model, movie_model)
+model.compile(optimizer=tf.keras.optimizers.Adagrad(learning_rate=0.08))
+cached_train = train.shuffle(int(df.shape[0]*0.9)).batch(int(df.shape[0]*0.9)).cache()
+cached_test = test.batch(int(df.shape[0]*0.15)).cache()
+path = os.path.join("/home/user/app/", "model/")
+cp_callback = tf.keras.callbacks.ModelCheckpoint(
+    filepath=path, 
+    verbose=1, 
+    save_weights_only=True,
+    save_freq=2)
+
+model.fit(cached_train, callbacks=[cp_callback],epochs=110)
+
+index=df["code"].map(lambda x: [model.movie_model(tf.constant(x))])
+
+indice=[]
+for i in range(0,1633):
+    indice.append(np.array(index)[i][0])
+
+searcher = scann.scann_ops_pybind.builder(np.array(indice), 10, "dot_product").tree(
+    num_leaves=1500, num_leaves_to_search=500, training_sample_size=df.shape[0]).score_brute_force(
+    2, quantize=True).build()
+
+import matplotlib.pyplot as plt
+
+def predict(text):
+    campos=str(text).lower()
+    query=np.sum([model.user_model(tf.constant(campos.split()[i])) for i in range(0,len(campos.split()))],axis=0)
+    neighbors, distances = searcher.search_batched([query])
+    xx = df.iloc[neighbors[0],:].nome_vaga
+    fig = plt.figure(figsize=(14,9))
+    plt.bar(list(xx),distances[0]*0.8*10)
+    plt.title('Degree of match')
+    plt.xlabel('Labels')
+    plt.xticks(rotation=270)
+
+    plt.ylabel('Distances')
+    for x, y in zip(list(range(0,10)),distances[0]*0.8*10):
+      plt.text(x, y, y, ha='center', va='bottom', fontsize=12, color='black')
+    return xx, fig
+
+demo = gr.Interface(fn=predict, inputs=gr.inputs.Textbox(label='CANDIDATE COMPETENCES - Click *Clear* before adding new input'), \
+    outputs=[gr.outputs.Textbox(label='SUGGESTED VACANCIES'),\
+      gr.Plot()],\
+        css='div {margin-left: auto; margin-right: auto; width: 100%;\
+            background-image: url("https://drive.google.com/uc?export=view&id=1KNnISAUcvh2Pt08f-EJZJYCIgkrKw3PI"); repeat 0 0;}')\
+              .launch(share=False)   

requirements.txt

@@ -0,0 +1,9 @@
+nltk==3.6.5
+pandas==1.3.4
+numpy==1.22.4
+matplotlib==3.4.3
+unidecode==1.2.0
+tensorflow==2.9.1
+scann==1.2.7
+tensorflow-recommenders==0.7.0
+