Upload 25 files

app.py

@@ -31,9 +31,12 @@ def __(form, mo, try_predict):
 
 @app.cell(hide_code=True)
 def __():
+    import os
+
     import marimo as mo
     import pandas as pd
     import numpy as np
+    import random
 
     import matplotlib.pyplot as plt
     import seaborn as sns
@@ -60,6 +63,8 @@ def __():
     from tensorflow.keras.preprocessing.sequence import pad_sequences
     from tensorflow.keras.callbacks import ReduceLROnPlateau, EarlyStopping
     from sklearn.model_selection import train_test_split
+    from sklearn.metrics import accuracy_score, classification_report
+    import joblib
 
     import nltk
 
@@ -84,13 +89,18 @@ def __():
         Word2Vec,
         WordCloud,
         WordNetLemmatizer,
+        accuracy_score,
         alt,
+        classification_report,
+        joblib,
         mo,
         nltk,
         np,
+        os,
         pad_sequences,
         pd,
         plt,
+        random,
         re,
         sns,
         stopwords,
@@ -162,7 +172,7 @@ def __():
     return issue_type_mapping, label_mapping
 
 
-@app.cell
+@app.cell(hide_code=True)
 def __(issue_type_mapping, label_mapping):
     label_mapping_reversed = {v: k for k, v in label_mapping.items()}
     issue_type_mapping_reversed = {v: k for k, v in issue_type_mapping.items()}
@@ -193,7 +203,7 @@ def __(df, issue_type_mapping_reversed, label_mapping_reversed, mo):
     return issue_types_grouped, labels_grouped
 
 
-@app.cell
+@app.cell(hide_code=True)
 def __(df):
     df.iloc[:, :6].head(7)
     return
@@ -336,8 +346,8 @@ def __(np):
 @app.cell(hide_code=True)
 def __(FastText, Word2Vec, processed_statement):
     embedding_models = {
-      'fasttext': FastText(sentences=processed_statement, vector_size=100, window=3, min_count=1, seed=0),
-      'word2vec': Word2Vec(sentences=processed_statement, vector_size=100, window=3, min_count=1, seed=0)
+      'fasttext': FastText(sentences=processed_statement, vector_size=100, window=3, min_count=1, seed=0, workers=1),
+      'word2vec': Word2Vec(sentences=processed_statement, vector_size=100, window=3, min_count=1, seed=0, workers=1)
     }
     return (embedding_models,)
 
@@ -444,8 +454,8 @@ def __(fasttext_plot, mo):
 
 
 @app.cell(hide_code=True)
-def __(fasttext_plot, mo, word2vec_plot):
-    word2vec_table = fasttext_plot.value[['statement', 'label_text', 'issue_type_text']]
+def __(mo, word2vec_plot):
+    word2vec_table = word2vec_plot.value[['statement', 'label_text', 'issue_type_text']]
     word2vec_chart = mo.vstack([
         word2vec_plot,
         word2vec_table
@@ -532,6 +542,11 @@ def __():
 
 @app.cell(hide_code=True)
 def __():
+    # seed_value = 345
+    # np.random.seed(seed_value)
+    # random.seed(seed_value)
+    # tf.random.set_seed(seed_value)
+
     # clf_model = Sequential()
     # clf_model.add(Bidirectional(tf.keras.layers.GRU(64, 
     #                                  activation='relu', 
@@ -558,18 +573,18 @@ def __():
 
 @app.cell(hide_code=True)
 def __():
-    # clf_model.save('models/model_8781.keras')
-    # joblib.dump(model_history, 'history/history_model_8781.pkl')
+    # clf_model.save('models/model_8719.keras')
+    # joblib.dump(model_history, 'history/history_model_8719.pkl')
     return
 
 
 @app.cell(hide_code=True)
-def __(joblib, tf):
-    loaded_model = tf.keras.models.load_model('models/model_8781.keras')
-    model_history_loaded = joblib.load('history/history_model_8781.pkl')
+def __(clf_model, model_history):
+    # loaded_model = tf.keras.models.load_model('models/model_8781.keras')
+    # model_history_loaded = joblib.load('history/history_model_8781.pkl')
 
-    # loaded_model = clf_model
-    # model_history_loaded = model_history
+    loaded_model = clf_model
+    model_history_loaded = model_history
     return loaded_model, model_history_loaded
 
 
@@ -620,13 +635,6 @@ def __(X_test, loaded_model, np):
     return (y_pred,)
 
 
-@app.cell(hide_code=True)
-def __():
-    from sklearn.metrics import accuracy_score, classification_report
-    import joblib
-    return accuracy_score, classification_report, joblib
-
-
 @app.cell(hide_code=True)
 def __(accuracy_score, mo, y_pred, y_test):
     mo.md(f"Accuracy score: **{round(accuracy_score(y_test, y_pred) * 100, 2)}**%")

history/history_model_8719.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3daad10fd31b82222443095e07d377da35c03b5bbd91bf83555c2f9d1a775b
+size 804041

history/history_model_8781.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcedb7cbde492115908c5e331f3359e56609c81f68bcff8b65246683f591bf75
-size 804042
+oid sha256:a9e877861152f54a2c5a1372a3d00c53d50e4ea24153ccc0d366a7fee3af6a79
+size 804041

history/history_model_8812.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a12c4820211896df8afa2345f2f122fec1dfd8b86f309f59634623ee0d69f546
+size 804027

requirements.txt

@@ -1,22 +1,22 @@
-marimo==0.9.15
-pandas==1.5.3
-numpy==1.24.2
-scipy==1.10.1
-pyarrow==16.1.0
-
-matplotlib==3.7.1
-seaborn==0.12.2
-altair==5.3.0
-
-umap-learn==0.5.7
-
-gensim==4.3.3
-scikit-learn>=0.22
-tensorflow==2.16.1
-wordcloud==1.9.3
-nltk==3.8.1
-
-# Or a specific version
-# marimo>=0.9.0
-
-# Add other dependencies as needed
+marimo==0.9.15
+pandas==1.5.3
+numpy==1.24.2
+scipy==1.10.1
+pyarrow==16.1.0
+
+matplotlib==3.7.1
+seaborn==0.12.2
+altair==5.3.0
+
+umap-learn==0.5.7
+
+gensim==4.3.3
+scikit-learn>=0.22
+tensorflow==2.16.1
+wordcloud==1.9.3
+nltk==3.8.1
+
+# Or a specific version
+# marimo>=0.9.0
+
+# Add other dependencies as needed