Logistic Regression¶

In this execise, I'd like you to perform a logistic regression on collecge applicant data.

This time, no explicit instructions, but here's the documentation for a Logistic Regression from SKLearn: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html

To simplify the dataset for this problem, I converted the "Chance of Admit" into a boolean "Admitted" column.

I've also done the train_test_split for you using sklearn's helpful helper function.

In [7]:

# 1. Load and clean the data
# I did this part for you!

from google.colab import drive
import pandas as pd

drive.mount('/content/gdrive')

df = pd.read_csv('/content/gdrive/My Drive/datasets/admission_predict.csv')

df["Admitted"] = df["Chance of Admit "] > 0.75
df.drop("Chance of Admit ", axis=1, inplace=True)
df.rename(columns={"LOR ": "LOR"}, inplace=True)

df

# 1. Load and clean the data # I did this part for you! from google.colab import drive import pandas as pd drive.mount('/content/gdrive') df = pd.read_csv('/content/gdrive/My Drive/datasets/admission_predict.csv') df["Admitted"] = df["Chance of Admit "] > 0.75 df.drop("Chance of Admit ", axis=1, inplace=True) df.rename(columns={"LOR ": "LOR"}, inplace=True) df

Drive already mounted at /content/gdrive; to attempt to forcibly remount, call drive.mount("/content/gdrive", force_remount=True).

Out[7]:

	Serial No.	GRE Score	TOEFL Score	University Rating	SOP	LOR	CGPA	Research	Admitted
0	1	337	118	4	4.5	4.5	9.65	1	True
1	2	324	107	4	4.0	4.5	8.87	1	True
2	3	316	104	3	3.0	3.5	8.00	1	False
3	4	322	110	3	3.5	2.5	8.67	1	True
4	5	314	103	2	2.0	3.0	8.21	0	False
...	...	...	...	...	...	...	...	...	...
395	396	324	110	3	3.5	3.5	9.04	1	True
396	397	325	107	3	3.0	3.5	9.11	1	True
397	398	330	116	4	5.0	4.5	9.45	1	True
398	399	312	103	3	3.5	4.0	8.78	0	False
399	400	333	117	4	5.0	4.0	9.66	1	True

400 rows × 9 columns

In [24]:

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression

# 2. Train/Test Split
df_train, df_test = train_test_split(df, test_size=0.2, random_state=42)

feature_cols = ["GRE Score", "TOEFL Score", "University Rating", "SOP", "LOR", "CGPA", "Research"]

# 3. Create X_train, y_train, X_test, y_test variables
X_train = df_train[feature_cols]
X_test = df_test[feature_cols]
y_train = df_train["Admitted"]
y_test = df_test["Admitted"]

# 4. Train the Model
model = LogisticRegression()
model.fit(X_train, y_train)

# 5. Evaluate the Model (Report Accuracy as correct/all)
y_pred = model.predict(X_test)

df_test["Predicted Admitted"] = y_pred

from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression # 2. Train/Test Split df_train, df_test = train_test_split(df, test_size=0.2, random_state=42) feature_cols = ["GRE Score", "TOEFL Score", "University Rating", "SOP", "LOR", "CGPA", "Research"] # 3. Create X_train, y_train, X_test, y_test variables X_train = df_train[feature_cols] X_test = df_test[feature_cols] y_train = df_train["Admitted"] y_test = df_test["Admitted"] # 4. Train the Model model = LogisticRegression() model.fit(X_train, y_train) # 5. Evaluate the Model (Report Accuracy as correct/all) y_pred = model.predict(X_test) df_test["Predicted Admitted"] = y_pred

/usr/local/lib/python3.10/dist-packages/sklearn/linear_model/_logistic.py:458: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(

In [25]:

correct_pred = len(df_test[df_test["Admitted"] == df_test["Predicted Admitted"]])
total_pred = len(df_test)

accuracy = correct_pred / total_pred

true_positives = len(df_test[(df_test["Admitted"] == True) & (df_test["Predicted Admitted"] == True)])
print(f"True Positives {true_positives}")

true_negatives = len(df_test[(df_test["Admitted"] == False) & (df_test["Predicted Admitted"] == False)])
print(f"True Negatives {true_negatives}")

false_positives = len(df_test[(df_test["Admitted"] == False) & (df_test["Predicted Admitted"] == True)])
print(f"False Positives {false_positives}")

false_negatives = len(df_test[(df_test["Admitted"] == True) & (df_test["Predicted Admitted"] == False)])
print(f"False Negatives {false_negatives}")

precision = true_positives / (true_positives + false_positives)
recall = true_positives / (true_positives + false_negatives)

print(f"Accuracy is {accuracy * 100}%")
print(f"Precision: {precision * 100}%")
print(f"Recall: {recall * 100}%")

correct_pred = len(df_test[df_test["Admitted"] == df_test["Predicted Admitted"]]) total_pred = len(df_test) accuracy = correct_pred / total_pred true_positives = len(df_test[(df_test["Admitted"] == True) & (df_test["Predicted Admitted"] == True)]) print(f"True Positives {true_positives}") true_negatives = len(df_test[(df_test["Admitted"] == False) & (df_test["Predicted Admitted"] == False)]) print(f"True Negatives {true_negatives}") false_positives = len(df_test[(df_test["Admitted"] == False) & (df_test["Predicted Admitted"] == True)]) print(f"False Positives {false_positives}") false_negatives = len(df_test[(df_test["Admitted"] == True) & (df_test["Predicted Admitted"] == False)]) print(f"False Negatives {false_negatives}") precision = true_positives / (true_positives + false_positives) recall = true_positives / (true_positives + false_negatives) print(f"Accuracy is {accuracy * 100}%") print(f"Precision: {precision * 100}%") print(f"Recall: {recall * 100}%")

True Positives 30
True Negatives 40
False Positives 8
False Negatives 2
Accuracy is 87.5%
Precision: 78.94736842105263%
Recall: 93.75%

In [ ]: