Upload 5 files

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text

Train.py

@@ -0,0 +1,48 @@
+import pandas as pd
+import numpy as np
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics import accuracy_score
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense, Dropout
+from tensorflow.keras.models import save_model
+from joblib import dump  # To save the TF-IDF vectorizer
+
+# 1. Read Data
+data = pd.read_excel('gender.xlsx')
+
+# 2. Preprocess Data
+data['Gender'] = data['Gender'].map({'M': 1, 'F': 0})
+
+# 3. Convert text data into numerical data using TF-IDF
+tfidf = TfidfVectorizer(analyzer='char', ngram_range=(1, 3))
+X = tfidf.fit_transform(data['Name']).toarray()  # Convert names into numerical features
+y = data['Gender'].values  # Labels: 1 for Male, 0 for Female
+
+# 4. Split the dataset into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# 5. Build the Neural Network Model
+model = Sequential()
+model.add(Dense(128, activation='relu', input_shape=(X_train.shape[1],)))
+model.add(Dropout(0.5))  # Add dropout to prevent overfitting
+model.add(Dense(64, activation='relu'))
+model.add(Dropout(0.5))
+model.add(Dense(1, activation='sigmoid'))  # Output layer with sigmoid for binary classification
+
+# 6. Compile the model
+model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
+
+# 7. Train the model with epochs
+model.fit(X_train, y_train, epochs=50, batch_size=32, validation_split=0.2)
+
+# 8. Save the model after training
+model.save('gender_prediction_model.h5')
+
+# 9. Save the TF-IDF vectorizer
+dump(tfidf, 'tfidf_vectorizer.joblib')
+
+# 10. Evaluate the model
+y_pred = (model.predict(X_test) > 0.5).astype("int32")  # Convert probabilities to binary output
+accuracy = accuracy_score(y_test, y_pred)
+print(f"Model Accuracy: {accuracy * 100:.2f}%")

Trained.py

@@ -0,0 +1,29 @@
+import pandas as pd
+import os
+from tensorflow.keras.models import load_model
+from joblib import load
+
+# Function to predict gender based on a name
+def predict_gender(name, model, tfidf):
+    vectorized_name = tfidf.transform([name]).toarray()  # Transform name into feature vector
+    gender = model.predict(vectorized_name) > 0.5  # Get prediction
+    return 'Male' if gender[0][0] == 1 else 'Female'
+
+# Load the pre-trained model
+model = load_model('gender_prediction_model.h5')
+
+# Check if the TF-IDF vectorizer file exists
+tfidf_vectorizer_file = 'tfidf_vectorizer.joblib'
+if not os.path.exists(tfidf_vectorizer_file):
+    raise FileNotFoundError(f"{tfidf_vectorizer_file} not found. Please ensure the file exists in the current directory.")
+
+# Load the TF-IDF vectorizer
+tfidf = load(tfidf_vectorizer_file)
+
+# Main loop to take user input for predictions
+while True:
+    name = input("Enter a name to predict gender (or type 'exit' to quit): ")
+    if name.lower() == 'exit':
+        break
+    predicted_gender = predict_gender(name, model, tfidf)
+    print(f"The predicted gender for '{name}' is: {predicted_gender}")

gender_prediction_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2cc4d6f2709ff0d838d5fb5694116cd806ba2ad2e714bc2ee8fce63dba34f03
+size 15286728