Skip to content
Snippets Groups Projects
Commit 0bd01afc authored by yl1r22's avatar yl1r22
Browse files

Upload New File

parent e89d6685
Branches
No related tags found
No related merge requests found
Show whitespace changes
Inline Side-by-side
Showing
with 326 additions and 0 deletions
AI_Part1.ipynb 0 → 100644
+ 326
− 0
View file @ 0bd01afc
%% Cell type:code id:6064e0b1 tags:
``` python
#Import scikit-learn dataset library
#from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn import svm, metrics
from sklearn.ensemble import RandomForestClassifier
from joblib import dump
from sklearn.metrics import confusion_matrix, f1_score
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
#Read training datasets
df = pd.read_csv('H:\AI classification\TrainingDataBinary.csv', header=None)
# Print the head of csv document to check
print(df.head(1))
# The first 128 columns are features
df_feature = df.iloc[:, :128]
# the 129th column is labels
df_label = df.iloc[:, 128]
# Split dataset into training set and test set
X_train, X_test, y_train, y_test = train_test_split(df_feature, df_label, test_size=0.2) # 80% training and 20% test
```
%% Output
0 1 2 3 4 5 \
0 70.399324 127673.0908 -49.572308 127648.0176 -169.578319 127723.2374
6 7 8 9 ... 119 120 121 122 123 \
0 65.689611 605.91099 -57.003571 626.78553 ... 0 0 0 0 0
124 125 126 127 128
0 0 0 0 0 0
[1 rows x 129 columns]
%% Cell type:code id:cdc65331 tags:
``` python
# Create a Randomforest Classifier
clf1 = RandomForestClassifier(n_estimators=100, max_features=78)
# Train the model using the training sets
clf1.fit(X_train, y_train)
# #Predict the response for test dataset
y_pred1 = clf1.predict(X_test)
print("Accuracy:",metrics.accuracy_score(y_test, y_pred1))
```
%% Output
Accuracy: 0.9741666666666666
%% Cell type:code id:12a28ae3 tags:
``` python
# Using Cross-validation to evaluate classifier
scores1 = cross_val_score(clf1, X_train, y_train, cv=5)
#Print model's Scores
print("Scores", scores1)
print("Mean Scores", np.mean(scores1))
```
%% Output
Scores [0.971875 0.97291667 0.96666667 0.978125 0.97916667]
Mean Scores 0.9737500000000001
%% Cell type:code id:16ad1a95 tags:
``` python
#Dump the model
dump(clf1, 'H:/AI classification/RFC_part1.pkl')
```
%% Output
['H:/AI classification/RFC_part1.pkl']
%% Cell type:code id:06c58b04 tags:
``` python
# Load testing dataset
test_data=pd.read_csv('H:\AI classification\TestingDataBinary.csv', header=None)
# Predict Testing dataset
predictions = clf1.predict(test_data) # Using clf1 model to predict
# Convert predictions into dataframe format
predictions_df = pd.DataFrame(predictions)
#Write the predictions to testing dataset
result = pd.concat([test_data,predictions_df], axis=1)
#Output a csv document
result.to_csv('H:/AI classification/test_pre1.csv', index = False, header = False)
```
%% Cell type:code id:c089a3e7 tags:
``` python
# print precdictions
print(predictions)
```
%% Output
[1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 1 1
1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]
%% Cell type:code id:47105ba9 tags:
``` python
# Create and print confusion matrix
conf_mat = confusion_matrix(y_test, y_pred1)
print("Confusion Matrix:")
print(conf_mat)
```
%% Output
Confusion Matrix:
[[591 14]
[ 17 578]]
%% Cell type:code id:e71eff12 tags:
``` python
# Calculating f1 score
f1 = f1_score(y_test, y_pred1)
print("F1 Score:", f1)
```
%% Output
F1 Score: 0.9738837405223252
%% Cell type:code id:57ae5f66 tags:
``` python
#Plotting confusion matixs
plt.figure(figsize=(10, 7))
sns.heatmap(conf_mat, annot=True, fmt='d', cmap='YlGnBu')
plt.xlabel('Predicted')
plt.ylabel('Actual')
plt.show()
```
%% Output
%% Cell type:code id:fef4fa06 tags:
``` python
#ROC curve plotting
#Calculate predicted scores, put positives into 1D array
y_score = clf1.predict_proba(X_test)
y_score_positive = y_score[:, 1]
# y_test is the true label，y_score_positive is predicted score
fpr, tpr, _ = roc_curve(y_test, y_score_positive)
roc_auc = auc(fpr, tpr)
#plotting the curve
plt.figure()
plt.plot(fpr, tpr, color='darkorange', lw=2, label='ROC curve (area = %0.2f)' % roc_auc)
plt.plot([0, 1], [0, 1], color='navy', lw=2, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver Operating Characteristic')
plt.legend(loc="lower right")
plt.show()
```
%% Output
%% Cell type:code id:e4a85cd9 tags:
``` python
```
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment