logistic_regression_MLmodel.txt

import pandas as pd
import psycopg2 as pg
import pandas.io.sql as psql
 
# get connected to the database
connection = pg.connect("dbname=mydatabase user=postgres")
 
dataframe = psql.frame_query("SELECT * FROM <tablename>", connection)
y = df["Outcome"]
X = df.drop(columns="Outcome")

#input baseball stats of players career- batting, feilding, awards. output = did they make the hall of fame.

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, 
                                                    y, 
                                                    random_state=1, 
                                                    stratify=y)
X_train.shape

classifier.fit(X_train, y_train)

LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
                   intercept_scaling=1, l1_ratio=None, max_iter=200,
                   multi_class='warn', n_jobs=None, penalty='l2',
                   random_state=1, solver='lbfgs', tol=0.0001, verbose=0,
                   warm_start=False)
                   
 y_pred = classifier.predict(X_test)
results = pd.DataFrame({"Prediction": y_pred, "Actual": y_test}).reset_index(drop=True)
results.head(20)

from sklearn.metrics import accuracy_score
print(accuracy_score(y_test, y_pred))