In [5]: df.

info()
In [1]: import numpy as np
import pandas as pd <class 'pandas.core.frame.DataFrame'>
RangeIndex: 400 entries, 0 to 399
Data columns (total 9 columns):
In [2]: df=pd.read_csv("Admission_Predict.csv") # Column Non-Null Count Dtype
df.head() --- ------ -------------- -----
0 Serial No. 400 non-null int64
Out[2]: 1 GRE Score 400 non-null int64
Serial No. GRE Score TOEFL Score University Rating SOP LOR CGPA Research Chance of Admit 2 TOEFL Score 400 non-null int64
0 1 337 118 4 4.5 4.5 9.65 1 0.92 3 University Rating 400 non-null int64
4 SOP 400 non-null float64
1 2 324 107 4 4.0 4.5 8.87 1 0.76 5 LOR 400 non-null float64
2 3 316 104 3 3.0 3.5 8.00 1 0.72
6 CGPA 400 non-null float64
7 Research 400 non-null int64
3 4 322 110 3 3.5 2.5 8.67 1 0.80 8 Chance of Admit 400 non-null float64
dtypes: float64(4), int64(5)
4 5 314 103 2 2.0 3.0 8.21 0 0.65
memory usage: 28.2 KB

In [3]: df.columns = df.columns.str.strip() In [6]: df.duplicated().sum()

Out[6]: 0
In [4]: df.shape

Out[4]: (400, 9) In [7]: df['Serial No.'].value_counts()

Out[7]: Serial No.

1 1
264 1
274 1
273 1
272 1
..
131 1
130 1
129 1
128 1
400 1
Name: count, Length: 400, dtype: int64

In [8]: if 'Chance of Admit' in df.columns: In [9]: from sklearn.model_selection import train_test_split

X = df.drop(columns=['Chance of Admit']) from sklearn.preprocessing import StandardScaler
y = df['Chance of Admit'] from tensorflow.keras.models import Sequential
else: from tensorflow.keras.layers import Dense
print("Column 'Chance of Admit' not found in the dataset.") from tensorflow.keras.optimizers import Adam
exit() ​
print("Shape of X:", X.shape) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1)
print("Shape of y:", y.shape) ​
scaler = StandardScaler()
Shape of X: (400, 8) X_train = scaler.fit_transform(X_train)
Shape of y: (400,) X_test = scaler.transform(X_test)
​
model = Sequential()
model.add(Dense(units=64, activation='relu', input_dim=X_train.shape[1]))
model.add(Dense(units=32, activation='relu'))
model.add(Dense(units=1))
​
model.compile(optimizer=Adam(), loss='mean_squared_error')
​
history = model.fit(X_train, y_train, epochs=100, validation_split=0.2, verbose=1)
​
test_loss = model.evaluate(X_test, y_test, verbose=0)
print(f"Test Loss: {test_loss}")
​
y_pred = model.predict(X_test)

Epoch 92/100
8/8 [==============================] - 0s 7ms/step - loss: 9.3117e-04 - val_loss: 0.0055
Epoch 93/100
8/8 [==============================] - 0s 6ms/step - loss: 8.9376e-04 - val_loss: 0.0054
Epoch 94/100
8/8 [==============================] - 0s 7ms/step - loss: 8.9198e-04 - val_loss: 0.0056
Epoch 95/100
8/8 [==============================] - 0s 7ms/step - loss: 8.6865e-04 - val_loss: 0.0054
Epoch 96/100
8/8 [==============================] - 0s 6ms/step - loss: 8.6995e-04 - val_loss: 0.0056
Epoch 97/100
8/8 [==============================] - 0s 7ms/step - loss: 8.7003e-04 - val_loss: 0.0054
Epoch 98/100
8/8 [==============================] - 0s 6ms/step - loss: 7.9774e-04 - val_loss: 0.0056
Epoch 99/100
8/8 [==============================] - 0s 6ms/step - loss: 8.2290e-04 - val_loss: 0.0056
Epoch 100/100
8/8 [==============================] - 0s 7ms/step - loss: 8.0702e-04 - val_loss: 0.0055
Test Loss: 0.006245521362870932
3/3 [==============================] - 0s 2ms/step

In [ ]: ​