Skip to content

Commit 83c87fc

Browse files
Janderion47Janderion47
committed
final proj
1 parent 84cf84e commit 83c87fc

File tree

4 files changed

+309
-0
lines changed

4 files changed

+309
-0
lines changed

‎.DS_Store‎

0 Bytes
Binary file not shown.

‎FinalJob.py‎

Lines changed: 176 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,176 @@
1+
import pandas as pd
2+
import numpy as np
3+
import matplotlib.pyplot as plt
4+
5+
from sklearn.linear_model import LogisticRegression
6+
from sklearn.preprocessing import StandardScaler
7+
from sklearn.metrics import classification_report, confusion_matrix
8+
9+
file1 = "Hospital1.txt"
10+
file2 = "Hospital2.txt"
11+
12+
try:
13+
data1 = pd.read_csv(file1)
14+
print("Yah yee the file loaded successfully!\n")
15+
print(data1.head())
16+
except FileNotFoundError:
17+
print(f"Error: '{file1}' not found. Check the filename and path.")
18+
except Exception as e:
19+
print("An error occurred while reading the file:", e)
20+
21+
num_readmitted = data1[" Readmission"].sum()
22+
23+
avg_staff = data1[" StaffSatisfaction"].mean()
24+
avg_clean = data1[" CleanlinessSatisfaction"].mean()
25+
avg_food = data1[" FoodSatisfaction"].mean()
26+
avg_comfort = data1[" ComfortSatisfaction"].mean()
27+
avg_comm = data1[" CommunicationSatisfaction"].mean()
28+
29+
print("-- Patient Satisfaction Summary --")
30+
print(f"Number of Patients Readmitted: {num_readmitted}")
31+
print(f"Average Staff Satisfaction: {avg_staff:.2f}")
32+
print(f"Average Cleanliness Satisfaction {avg_clean:.2f}")
33+
print(f"Average Food Satisfaction: {avg_food:.2f}")
34+
print(f"Average Comfort Satisfaction: {avg_comfort:.2f}")
35+
print(f"Average Communication Satisfaction: {avg_comm:.2f}")
36+
37+
try:
38+
data2 = pd.read_csv(file2)
39+
print("Yah yee the file loaded successfully!\n")
40+
print(data1.head())
41+
except FileNotFoundError:
42+
print(f"Error: '{file2}' not found. Check the filename and path.")
43+
except Exception as e:
44+
print("An error occurred while reading the file:", e)
45+
46+
num_readmitted2 = data2[" Readmission"].sum()
47+
48+
avg_staff2 = data2[" StaffSatisfaction"].mean()
49+
avg_clean2 = data2[" CleanlinessSatisfaction"].mean()
50+
avg_food2 = data2[" FoodSatisfaction"].mean()
51+
avg_comfort2 = data2[" ComfortSatisfaction"].mean()
52+
avg_comm2 = data2[" CommunicationSatisfaction"].mean()
53+
54+
print("-- Patient Satisfaction Summary --")
55+
print(f"Number of Patients Readmitted: {num_readmitted2}")
56+
print(f"Average Staff Satisfaction: {avg_staff2:.2f}")
57+
print(f"Average Cleanliness Satisfaction {avg_clean2:.2f}")
58+
print(f"Average Food Satisfaction: {avg_food2:.2f}")
59+
print(f"Average Comfort Satisfaction: {avg_comfort2:.2f}")
60+
print(f"Average Communication Satisfaction: {avg_comm2:.2f}")
61+
62+
63+
satisfaction_columns = [
64+
" StaffSatisfaction"," CleanlinessSatisfaction"," FoodSatisfaction",
65+
" ComfortSatisfaction"," CommunicationSatisfaction"
66+
]
67+
data1["OverallSatisfaction"] = data1[satisfaction_columns].mean(axis=1)
68+
print(data1[["PatientID","OverallSatisfaction"," Readmission"]].head())
69+
70+
71+
X1 = data1[["OverallSatisfaction"]].values
72+
y1 = data1[" Readmission"].values
73+
74+
scaler1 = StandardScaler()
75+
X_scaled1 = scaler1.fit_transform(X1)
76+
77+
log_reg1 = LogisticRegression()
78+
log_reg1.fit(X_scaled1,y1)
79+
80+
coef = log_reg1.coef_[0][0]
81+
intercept = log_reg1.intercept_[0]
82+
83+
print("-- Logistic Regression Coefficeints --")
84+
print(f"Intercept: {intercept:.3f}")
85+
print(f"Coefficient for Overall Satisfaction: {coef:.3f}")
86+
87+
if coef < 0:
88+
direction = "Higher satisfaction is associated with LOWER probability of readmission."
89+
elif coef > 0:
90+
direction = "Higher satisfaction is associated with HIGHER probability of readmission."
91+
else:
92+
direction = "No apparaent association between satisfaction and readmission."
93+
94+
print("\nInterpretation:")
95+
print(direction)
96+
97+
98+
x_range1 = np.linspace(data1["OverallSatisfaction"].min(),data1["OverallSatisfaction"].max(),100).reshape(-1,1)
99+
x_range_scaled1 = scaler1.transform(x_range1)
100+
y_prob1 = log_reg1.predict_proba(x_range_scaled1)[:,1]
101+
102+
plt.figure(figsize=(8,5))
103+
plt.scatter(data1["OverallSatisfaction"],data1[" Readmission"],label="Observed Data", alpha=0.7)
104+
plt.plot(x_range1, y_prob1,label="Logistic Regression Curve",linewidth=2)
105+
106+
plt.xlabel("Overall Satisfaction")
107+
plt.ylabel("Probability of Readmission (1 = Yes)")
108+
plt.title("Logistic Regression: Readmission vs Overall Satisfaction")
109+
plt.legend()
110+
plt.grid(True)
111+
plt.show()
112+
113+
114+
y_pred1 = log_reg1.predict(X_scaled1)
115+
print("-- Classification Report --")
116+
print(classification_report(y1,y_pred1,zero_division=0))
117+
print("-- Confusion Matrix --")
118+
print(confusion_matrix(y1,y_pred1))
119+
120+
121+
satisfaction_columns = [
122+
" StaffSatisfaction"," CleanlinessSatisfaction"," FoodSatisfaction",
123+
" ComfortSatisfaction"," CommunicationSatisfaction"
124+
]
125+
data2["OverallSatisfaction"] = data2[satisfaction_columns].mean(axis=1)
126+
print(data2[["PatientID","OverallSatisfaction"," Readmission"]].head())
127+
128+
129+
X2 = data2[["OverallSatisfaction"]].values
130+
y2 = data2[" Readmission"].values
131+
132+
scaler2 = StandardScaler()
133+
X_scaled2 = scaler2.fit_transform(X2)
134+
135+
log_reg2 = LogisticRegression()
136+
log_reg2.fit(X_scaled2,y2)
137+
138+
coef2 = log_reg2.coef_[0][0]
139+
intercept2 = log_reg2.intercept_[0]
140+
141+
print("-- Logistic Regression Coefficeints --")
142+
print(f"Intercept: {intercept:.3f}")
143+
print(f"Coefficient for Overall Satisfaction: {coef:.3f}")
144+
145+
if coef < 0:
146+
direction = "Higher satisfaction is associated with LOWER probability of readmission."
147+
elif coef > 0:
148+
direction = "Higher satisfaction is associated with HIGHER probability of readmission."
149+
else:
150+
direction = "No apparaent association between satisfaction and readmission."
151+
152+
print("\nInterpretation:")
153+
print(direction)
154+
155+
156+
x_range2 = np.linspace(data2["OverallSatisfaction"].min(),data2["OverallSatisfaction"].max(),100).reshape(-1,1)
157+
x_range_scaled2 = scaler2.transform(x_range2)
158+
y_prob2 = log_reg2.predict_proba(x_range_scaled2)[:,1]
159+
160+
plt.figure(figsize=(8,5))
161+
plt.scatter(data2["OverallSatisfaction"],data2[" Readmission"],label="Observed Data", alpha=0.7)
162+
plt.plot(x_range2, y_prob2,label="Logistic Regression Curve",linewidth=2)
163+
164+
plt.xlabel("Overall Satisfaction")
165+
plt.ylabel("Probability of Readmission (1 = Yes)")
166+
plt.title("Logistic Regression: Readmission vs Overall Satisfaction")
167+
plt.legend()
168+
plt.grid(True)
169+
plt.show()
170+
171+
172+
y_pred2 = log_reg2.predict(X_scaled2)
173+
print("-- Classification Report --")
174+
print(classification_report(y2,y_pred2,zero_division=0))
175+
print("-- Confusion Matrix --")
176+
print(confusion_matrix(y2,y_pred2))

‎Hospital1.txt‎

Lines changed: 75 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,75 @@
1+
PatientID, Readmission, StaffSatisfaction, CleanlinessSatisfaction, FoodSatisfaction, ComfortSatisfaction, CommunicationSatisfaction
2+
101, 1, 4, 5, 3, 4, 5
3+
102, 0, 3, 2, 4, 2, 3
4+
103, 1, 5, 4, 5, 4, 4
5+
104, 0, 5, 3, 5, 4, 5
6+
105, 1, 4, 5, 3, 4, 4
7+
106, 1, 2, 3, 2, 3, 3
8+
107, 0, 3, 2, 3, 4, 3
9+
108, 0, 5, 5, 4, 5, 5
10+
109, 1, 4, 4, 4, 4, 4
11+
110, 0, 3, 3, 3, 4, 3
12+
111, 1, 4, 5, 4, 4, 5
13+
112, 0, 2, 3, 2, 3, 2
14+
113, 1, 3, 4, 3, 4, 3
15+
114, 1, 3, 3, 3, 2, 3
16+
115, 0, 5, 4, 5, 5, 5
17+
116, 1, 4, 3, 4, 4, 4
18+
117, 0, 2, 2, 2, 3, 3
19+
118, 0, 5, 5, 4, 4, 5
20+
119, 1, 4, 4, 4, 4, 4
21+
120, 0, 3, 3, 3, 4, 3
22+
121, 1, 4, 5, 5, 4, 4
23+
122, 1, 3, 4, 4, 4, 3
24+
123, 0, 4, 3, 4, 3, 4
25+
124, 0, 2, 2, 2, 3, 3
26+
125, 1, 3, 4, 3, 4, 3
27+
126, 0, 4, 5, 5, 5, 5
28+
127, 1, 3, 4, 4, 4, 3
29+
128, 0, 4, 3, 4, 3, 4
30+
129, 0, 2, 2, 2, 3, 3
31+
130, 1, 3, 4, 3, 4, 3
32+
131, 1, 4, 5, 3, 4, 5
33+
132, 0, 3, 2, 4, 2, 3
34+
133, 1, 5, 4, 5, 4, 4
35+
134, 0, 5, 3, 5, 4, 5
36+
135, 1, 4, 5, 3, 4, 4
37+
136, 1, 2, 3, 2, 3, 3
38+
137, 0, 3, 2, 3, 4, 3
39+
138, 0, 5, 5, 4, 5, 5
40+
139, 1, 4, 4, 4, 4, 4
41+
140, 0, 3, 3, 3, 4, 3
42+
141, 1, 4, 5, 4, 4, 5
43+
142, 0, 2, 3, 2, 3, 2
44+
143, 1, 3, 4, 3, 4, 3
45+
144, 1, 3, 3, 3, 2, 3
46+
145, 0, 5, 4, 5, 5, 5
47+
146, 1, 4, 3, 4, 4, 4
48+
147, 0, 2, 2, 2, 3, 3
49+
148, 0, 5, 5, 4, 4, 5
50+
149, 1, 4, 4, 4, 4, 4
51+
150, 0, 3, 3, 3, 4, 3
52+
151, 1, 4, 5, 5, 4, 4
53+
152, 1, 3, 4, 4, 4, 3
54+
153, 0, 4, 3, 4, 3, 4
55+
154, 0, 2, 2, 2, 3, 3
56+
155, 1, 3, 4, 3, 4, 3
57+
156, 0, 4, 5, 5, 5, 5
58+
157, 1, 3, 4, 4, 4, 3
59+
158, 0, 4, 3, 4, 3, 4
60+
159, 0, 2, 2, 2, 3, 3
61+
160, 1, 3, 4, 3, 4, 3
62+
161, 1, 4, 5, 3, 4, 5
63+
162, 0, 3, 2, 4, 2, 3
64+
163, 1, 5, 4, 5, 4, 4
65+
164, 0, 5, 3, 5, 4, 5
66+
165, 1, 4, 5, 3, 4, 4
67+
166, 1, 2, 3, 2, 3, 3
68+
167, 0, 3, 2, 3, 4, 3
69+
168, 0, 5, 5, 4, 5, 5
70+
169, 1, 4, 4, 4, 4, 4
71+
170, 0, 3, 3, 3, 4, 3
72+
171, 1, 4, 5, 4, 4, 5
73+
172, 0, 2, 3, 2, 3, 2
74+
173, 1, 3, 4, 3, 4, 3
75+
174, 1, 3, 3, 3, 2, 3

‎Hospital2.txt‎

Lines changed: 58 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,58 @@
1+
PatientID, Readmission, StaffSatisfaction, CleanlinessSatisfaction, FoodSatisfaction, ComfortSatisfaction, CommunicationSatisfaction
2+
101, 1, 4, 5, 3, 4, 5
3+
102, 0, 3, 2, 4, 2, 3
4+
103, 1, 5, 4, 5, 4, 4
5+
104, 0, 5, 3, 5, 4, 5
6+
105, 1, 4, 5, 3, 4, 4
7+
106, 1, 2, 3, 2, 3, 3
8+
107, 0, 3, 2, 3, 4, 3
9+
108, 0, 5, 5, 4, 5, 5
10+
109, 1, 4, 4, 4, 4, 4
11+
110, 0, 3, 3, 3, 4, 3
12+
111, 1, 4, 5, 4, 4, 5
13+
112, 0, 2, 3, 2, 3, 2
14+
113, 1, 3, 4, 3, 4, 3
15+
114, 1, 3, 3, 3, 2, 3
16+
115, 0, 5, 4, 5, 5, 5
17+
116, 1, 4, 3, 4, 4, 4
18+
117, 0, 2, 2, 2, 3, 3
19+
118, 0, 5, 5, 4, 4, 5
20+
119, 1, 4, 4, 4, 4, 4
21+
120, 0, 3, 3, 3, 4, 3
22+
121, 1, 4, 5, 5, 4, 4
23+
122, 1, 3, 4, 4, 4, 3
24+
123, 0, 4, 3, 4, 3, 4
25+
124, 0, 2, 2, 2, 3, 3
26+
125, 1, 3, 4, 3, 4, 3
27+
126, 0, 4, 5, 5, 5, 5
28+
127, 1, 3, 4, 4, 4, 3
29+
128, 0, 4, 3, 4, 3, 4
30+
129, 0, 2, 2, 2, 3, 3
31+
130, 1, 3, 4, 3, 4, 3
32+
131, 1, 4, 5, 3, 4, 5
33+
132, 0, 3, 2, 4, 2, 3
34+
133, 1, 5, 4, 5, 4, 4
35+
134, 0, 5, 3, 5, 4, 5
36+
135, 1, 4, 5, 3, 4, 4
37+
136, 1, 2, 3, 2, 3, 3
38+
137, 0, 3, 2, 3, 4, 3
39+
138, 0, 5, 5, 4, 5, 5
40+
139, 1, 4, 4, 4, 4, 4
41+
140, 0, 3, 3, 3, 4, 3
42+
141, 1, 4, 5, 4, 4, 5
43+
142, 0, 2, 3, 2, 3, 2
44+
143, 1, 3, 4, 3, 4, 3
45+
144, 1, 3, 3, 3, 2, 3
46+
145, 0, 5, 4, 5, 5, 5
47+
146, 1, 4, 3, 4, 4, 4
48+
147, 0, 2, 2, 2, 3, 3
49+
148, 0, 5, 5, 4, 4, 5
50+
149, 1, 4, 4, 4, 4, 4
51+
150, 0, 3, 3, 3, 4, 3
52+
151, 1, 4, 5, 5, 4, 4
53+
152, 1, 3, 4, 4, 4, 3
54+
153, 0, 4, 3, 4, 3, 4
55+
154, 0, 2, 2, 2, 3, 3
56+
155, 1, 3, 4, 3, 4, 3
57+
156, 0, 4, 5, 5, 5, 5
58+
157, 1, 3, 4, 4, 4, 3

0 commit comments

Comments
 (0)