MrAR commited on
Commit
e0f5da7
·
verified ·
1 Parent(s): 3d56fff

Upload 9 files

Browse files
Files changed (9) hide show
  1. .gitattributes +35 -35
  2. README.md +13 -13
  3. app.py +59 -111
  4. continuous_cols.pkl +3 -0
  5. feature_names.pkl +3 -0
  6. models.pkl +3 -0
  7. ratios.pkl +3 -0
  8. requirements.txt +0 -2
  9. scaler.pkl +3 -0
.gitattributes CHANGED
@@ -1,35 +1,35 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,13 +1,13 @@
1
- ---
2
- title: HeartSense
3
- emoji: 📊
4
- colorFrom: purple
5
- colorTo: indigo
6
- sdk: gradio
7
- sdk_version: 4.41.0
8
- app_file: app.py
9
- pinned: false
10
- license: apache-2.0
11
- ---
12
-
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
+ ---
2
+ title: HeartSense
3
+ emoji: 📊
4
+ colorFrom: purple
5
+ colorTo: indigo
6
+ sdk: gradio
7
+ sdk_version: 4.41.0
8
+ app_file: app.py
9
+ pinned: false
10
+ license: apache-2.0
11
+ ---
12
+
13
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py CHANGED
@@ -1,101 +1,26 @@
1
- import pandas as pd
2
  import numpy as np
3
- import matplotlib.pyplot as plt
4
- import seaborn as sns
5
  import gradio as gr
6
- from sklearn.model_selection import train_test_split
7
- from sklearn.preprocessing import LabelEncoder, StandardScaler
8
- from sklearn.linear_model import LogisticRegression
9
- from sklearn.tree import DecisionTreeClassifier, plot_tree
10
- from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier
11
- from sklearn.svm import SVC
12
- from sklearn.neighbors import KNeighborsClassifier
13
- from xgboost import XGBClassifier
14
- from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix
15
-
16
- # Load dataset
17
- mydata = pd.read_csv("eda_heart.csv")
18
-
19
-
20
- # Remove duplicates
21
- mydata = mydata.drop_duplicates()
22
-
23
-
24
- # Outlier removal using IQR
25
- variables = ["Age", "RestingBP", "Cholesterol", "MaxHR", "Oldpeak"]
26
- for col in variables:
27
- q1 = mydata[col].quantile(0.25)
28
- q3 = mydata[col].quantile(0.75)
29
- iqr = q3 - q1
30
- lower_bound = q1 - 1.5 * iqr
31
- upper_bound = q3 + 1.5 * iqr
32
- mydata = mydata[(mydata[col] >= lower_bound) & (mydata[col] <= upper_bound)]
33
-
34
-
35
- # Label Encoding
36
- label_encoders = {}
37
- for col in ["Sex", "ChestPainType", "RestingECG", "ExerciseAngina", "ST_Slope"]:
38
- le = LabelEncoder()
39
- mydata[col] = le.fit_transform(mydata[col])
40
- label_encoders[col] = le
41
-
42
-
43
- # Splitting Data
44
- X = mydata.drop("HeartDisease", axis=1)
45
- y = mydata["HeartDisease"]
46
- X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=123)
47
 
 
 
 
48
 
49
- # Scaling continuous variables
50
- scaler = StandardScaler()
51
- continuous_cols = ["Age", "RestingBP", "Cholesterol", "MaxHR", "Oldpeak"]
52
- X_train[continuous_cols] = scaler.fit_transform(X_train[continuous_cols])
53
- X_test[continuous_cols] = scaler.transform(X_test[continuous_cols])
54
 
 
 
55
 
56
- # Model Training and Evaluation
57
- models = {
58
- "Logistic Regression": LogisticRegression(),
59
- "Decision Tree": DecisionTreeClassifier(),
60
- "Gradient Boosting": GradientBoostingClassifier(),
61
- "KNN": KNeighborsClassifier(n_neighbors=5),
62
- "SVM": SVC(kernel='linear'),
63
- "Random Forest": RandomForestClassifier(n_estimators=100),
64
- "XGBoost": XGBClassifier(use_label_encoder=False, eval_metric='logloss')
65
- }
66
 
67
- results = []
68
- for name, model in models.items():
69
- model.fit(X_train, y_train)
70
- y_pred = model.predict(X_test)
71
- accuracy = accuracy_score(y_test, y_pred)
72
- precision = precision_score(y_test, y_pred)
73
- recall = recall_score(y_test, y_pred)
74
- f1 = f1_score(y_test, y_pred)
75
- results.append([name, accuracy, precision, recall, f1])
76
-
77
- # Convert results to DataFrame
78
- results_df = pd.DataFrame(results, columns=["Model", "Accuracy", "Precision", "Recall", "F1_Score"])
79
-
80
- # Calculate metrics
81
- metrics = results_df[["Model", "Accuracy", "F1_Score", "Precision"]].copy()
82
- metrics["Metric"] = (metrics["Accuracy"] * metrics["F1_Score"]) / metrics["Precision"]
83
-
84
- # Calculate average metric and ratios
85
- avg_metric = metrics["Metric"].mean()
86
- metrics["Ratio"] = metrics["Metric"] / avg_metric
87
-
88
- # Create a dictionary for ratios
89
- ratios = dict(zip(metrics["Model"], metrics["Ratio"]))
90
-
91
-
92
-
93
- trained_models = {}
94
- for name, model in models.items():
95
- model.fit(X_train, y_train)
96
- trained_models[name] = model
97
 
98
  def predict_heart_disease(age, resting_bp, cholesterol, max_hr, oldpeak, fasting_bs, sex, chest_pain_type, resting_ecg, exercise_angina, st_slope):
 
99
  sex = 1 if sex == "Male" else 0
100
  chest_pain_type_mapping = {"ASY": 1, "ATA": 2, "NAP": 3, "TA": 4}
101
  chest_pain_type = chest_pain_type_mapping[chest_pain_type]
@@ -105,38 +30,61 @@ def predict_heart_disease(age, resting_bp, cholesterol, max_hr, oldpeak, fasting
105
  exercise_angina = exercise_angina_mapping[exercise_angina]
106
  st_slope_mapping = {"Up": 1, "Flat": 2, "Down": 3}
107
  st_slope = st_slope_mapping[st_slope]
 
 
108
  input_data = np.array([[age, resting_bp, cholesterol, max_hr, oldpeak, sex, chest_pain_type, resting_ecg, exercise_angina, st_slope, fasting_bs]])
109
  input_df = pd.DataFrame(input_data, columns=["Age", "RestingBP", "Cholesterol", "MaxHR", "Oldpeak", "Sex", "ChestPainType", "RestingECG", "ExerciseAngina", "ST_Slope", "FastingBS"])
110
- input_df = input_df[X_train.columns]
 
 
 
 
111
  input_df[continuous_cols] = scaler.transform(input_df[continuous_cols])
 
 
112
  predictions = {name: model.predict(input_df)[0] for name, model in trained_models.items()}
113
- # Calculate weight values and sum them
 
114
  total_weight = sum(prediction * ratios[name] for name, prediction in predictions.items())
 
115
  # Determine output based on total weight
116
  if total_weight > 3.5:
117
- output = "You might get a heart stroke take precautions"
118
  else:
119
- output = "You are safe"
120
- return output
121
-
122
-
 
 
 
 
 
 
 
123
  iface = gr.Interface(
124
  fn=predict_heart_disease,
125
  inputs=[
126
- gr.Number(label="Age"),
127
- gr.Number(label="RestingBP"),
128
- gr.Number(label="Cholesterol"),
129
- gr.Number(label="MaxHR"),
130
- gr.Number(label="Oldpeak (0-2)"),
131
- gr.Number(label="FastingBS"),
132
- gr.Radio(["Female", "Male"], label="Sex"),
133
- gr.Radio(["ASY", "ATA", "NAP", "TA"], label="Chest Pain Type"),
134
- gr.Radio(["Normal", "ST", "LVH"], label="Resting ECG"),
135
- gr.Radio(["No", "Yes"], label="Exercise Angina"),
136
- gr.Radio(["Up", "Flat", "Down"], label="ST Slope"),
137
  ],
138
- outputs=gr.Text(),
139
- title="Heart Disease Prediction",
140
- description="Enter patient details to predict heart disease risk using multiple models."
 
 
 
 
141
  )
142
- iface.launch()
 
 
 
 
1
  import numpy as np
2
+ import pandas as pd
 
3
  import gradio as gr
4
+ import pickle
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
 
6
+ # Load all saved components
7
+ with open('models.pkl', 'rb') as f:
8
+ trained_models = pickle.load(f)
9
 
10
+ with open('scaler.pkl', 'rb') as f:
11
+ scaler = pickle.load(f)
 
 
 
12
 
13
+ with open('ratios.pkl', 'rb') as f:
14
+ ratios = pickle.load(f)
15
 
16
+ with open('feature_names.pkl', 'rb') as f:
17
+ feature_names = pickle.load(f)
 
 
 
 
 
 
 
 
18
 
19
+ with open('continuous_cols.pkl', 'rb') as f:
20
+ continuous_cols = pickle.load(f)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
 
22
  def predict_heart_disease(age, resting_bp, cholesterol, max_hr, oldpeak, fasting_bs, sex, chest_pain_type, resting_ecg, exercise_angina, st_slope):
23
+ # Encode categorical inputs
24
  sex = 1 if sex == "Male" else 0
25
  chest_pain_type_mapping = {"ASY": 1, "ATA": 2, "NAP": 3, "TA": 4}
26
  chest_pain_type = chest_pain_type_mapping[chest_pain_type]
 
30
  exercise_angina = exercise_angina_mapping[exercise_angina]
31
  st_slope_mapping = {"Up": 1, "Flat": 2, "Down": 3}
32
  st_slope = st_slope_mapping[st_slope]
33
+
34
+ # Create input array
35
  input_data = np.array([[age, resting_bp, cholesterol, max_hr, oldpeak, sex, chest_pain_type, resting_ecg, exercise_angina, st_slope, fasting_bs]])
36
  input_df = pd.DataFrame(input_data, columns=["Age", "RestingBP", "Cholesterol", "MaxHR", "Oldpeak", "Sex", "ChestPainType", "RestingECG", "ExerciseAngina", "ST_Slope", "FastingBS"])
37
+
38
+ # Reorder columns to match training data
39
+ input_df = input_df[feature_names]
40
+
41
+ # Scale continuous features
42
  input_df[continuous_cols] = scaler.transform(input_df[continuous_cols])
43
+
44
+ # Get predictions from all models
45
  predictions = {name: model.predict(input_df)[0] for name, model in trained_models.items()}
46
+
47
+ # Calculate weighted sum
48
  total_weight = sum(prediction * ratios[name] for name, prediction in predictions.items())
49
+
50
  # Determine output based on total weight
51
  if total_weight > 3.5:
52
+ output = "⚠️ Warning: You might be at risk of heart disease. Please consult a healthcare professional for proper evaluation."
53
  else:
54
+ output = "✓ Based on the input parameters, your risk appears to be lower. However, always consult with a healthcare professional for accurate diagnosis."
55
+
56
+ # Add individual model predictions for transparency
57
+ model_results = "\n\nIndividual Model Predictions:\n"
58
+ for name, pred in predictions.items():
59
+ result = "Disease" if pred == 1 else "No Disease"
60
+ model_results += f"- {name}: {result}\n"
61
+
62
+ return output + model_results
63
+
64
+ # Create Gradio interface
65
  iface = gr.Interface(
66
  fn=predict_heart_disease,
67
  inputs=[
68
+ gr.Number(label="Age", value=50),
69
+ gr.Number(label="Resting BP (mm Hg)", value=120),
70
+ gr.Number(label="Cholesterol (mg/dL)", value=200),
71
+ gr.Number(label="Max Heart Rate", value=150),
72
+ gr.Number(label="Oldpeak (0-2)", value=0),
73
+ gr.Number(label="Fasting Blood Sugar (0 or 1)", value=0),
74
+ gr.Radio(["Female", "Male"], label="Sex", value="Male"),
75
+ gr.Radio(["ASY", "ATA", "NAP", "TA"], label="Chest Pain Type", value="ASY"),
76
+ gr.Radio(["Normal", "ST", "LVH"], label="Resting ECG", value="Normal"),
77
+ gr.Radio(["No", "Yes"], label="Exercise Angina", value="No"),
78
+ gr.Radio(["Up", "Flat", "Down"], label="ST Slope", value="Flat"),
79
  ],
80
+ outputs=gr.Textbox(label="Prediction Result", lines=10),
81
+ title="❤️ Heart Disease Prediction System",
82
+ description="Enter patient details to predict heart disease risk using an ensemble of 7 machine learning models. This tool is for educational purposes only and should not replace professional medical advice.",
83
+ examples=[
84
+ [55, 130, 250, 140, 1.0, 0, "Male", "ASY", "Normal", "No", "Flat"],
85
+ [45, 110, 180, 160, 0, 0, "Female", "NAP", "Normal", "No", "Up"],
86
+ ]
87
  )
88
+
89
+ if __name__ == "__main__":
90
+ iface.launch()
continuous_cols.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ea12475e0930f836685e606159ea3e731b7a66e6d58a3bc1a9037292cd6da2
3
+ size 66
feature_names.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39159db5bf9aa8aaea40f16debd43d6767dd0a4511cdba92f78fa762225e7612
3
+ size 141
models.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2403fc12a689cbfa5ab8ab02ecdcc6e81bbedf3e31507e39a90ea74ac22b48
3
+ size 1586741
ratios.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f356443de98848eb79e2c3194323b79c152fa026e45480941ed8173cd1d90a39
3
+ size 175
requirements.txt CHANGED
@@ -1,7 +1,5 @@
1
  pandas
2
  numpy
3
- matplotlib
4
- seaborn
5
  gradio
6
  scikit-learn
7
  xgboost
 
1
  pandas
2
  numpy
 
 
3
  gradio
4
  scikit-learn
5
  xgboost
scaler.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c062f18f51960f1a6a03c3f6b9c3993d24aa2ce117ed4f00d9bf9042bbc0a932
3
+ size 706