Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit c9f86b2

Browse files
ICTAcadamy
1 parent 02f9982 commit c9f86b2

File tree

7 files changed

+130
-0
lines changed

7 files changed

+130
-0
lines changed

‎ICTAcadamy/Week-1/BreastCancer.py‎

Lines changed: 27 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,27 @@
1+
import numpy as np
2+
from sklearn import datasets
3+
from sklearn.model_selection import train_test_split, GridSearchCV
4+
from sklearn.svm import SVC
5+
from sklearn.metrics import accuracy_score
6+
7+
8+
breast_cancer = datasets.load_breast_cancer()
9+
X = breast_cancer.data
10+
y = breast_cancer.target
11+
12+
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
13+
14+
svm = SVC(kernel='rbf')
15+
param_grid = {
16+
'C': [0.1, 1, 10],
17+
'gamma': [0.001, 0.01, 0.1, 1]
18+
}
19+
20+
grid_search = GridSearchCV(estimator=svm, param_grid=param_grid, cv=5)
21+
grid_search.fit(X_train, y_train)
22+
best_params = grid_search.best_params_
23+
best_model = grid_search.best_estimator_
24+
y_pred = best_model.predict(X_test)
25+
accuracy = accuracy_score(y_test, y_pred)
26+
27+
print(accuracy)

‎ICTAcadamy/Week-1/DataFrame.py‎

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
import pandas as pd
2+
3+
data={'a':[1,2],'b':[3,4],'c':[5,6]}
4+
5+
df=pd.DataFrame(data)
6+
7+
def float_value(x):
8+
return x*1.0
9+
10+
df=df.apply(float_value)
11+
12+
print(df)
Lines changed: 29 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
1+
import numpy as np
2+
import pandas as pd
3+
from sklearn.datasets import load_breast_cancer
4+
from sklearn.feature_selection import RFE
5+
from sklearn.linear_model import LogisticRegression
6+
7+
breast_cancer = load_breast_cancer()
8+
X = breast_cancer.data
9+
y = breast_cancer.target
10+
11+
feature_names = breast_cancer.feature_names
12+
df = pd.DataFrame(X, columns=feature_names)
13+
14+
15+
model = LogisticRegression()
16+
num_features_to_select = 5
17+
rfe = RFE(estimator=model, n_features_to_select=num_features_to_select)
18+
rfe.fit(X, y)
19+
20+
21+
selected_features = df.columns[rfe.support_]
22+
feature_ranking = rfe.ranking_
23+
24+
feature_rank_df = pd.DataFrame({'Feature': df.columns, 'Ranking': feature_ranking})
25+
26+
sorted_feature_rank_df = feature_rank_df.sort_values(by='Ranking')
27+
28+
print("Top {} Features:".format(num_features_to_select))
29+
print(sorted_feature_rank_df.head(num_features_to_select))

‎ICTAcadamy/Week-1/MergeFrame.py‎

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
import pandas as pd
2+
3+
df1 = pd.DataFrame([['a', 1, 2], ['b', 2, 3], ['c', 4, 5]], columns=['A', 'B', 'C'])
4+
df2 = pd.DataFrame([['a', 6, 7], ['a', 8, 9]], columns=['A', 'D', 'E'])
5+
6+
7+
merged_df = df1.merge(df2, on='A', how='left')
8+
9+
print(merged_df)

‎ICTAcadamy/Week-1/SKlearn.py‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,23 @@
1+
from sklearn.metrics import precision_score, recall_score, confusion_matrix
2+
3+
x=[1,0,0,1,1]
4+
y=[0,1,0,1,0]
5+
6+
precision=precision_score(x,y)
7+
recall=recall_score(x,y)
8+
9+
print("Precision API : ",precision);
10+
print("Recall API : ",recall);
11+
12+
mat=confusion_matrix(x,y)
13+
14+
true_negative=mat[0,0]
15+
true_positive=mat[1,1]
16+
false_negative=mat[0,1]
17+
false_positive=mat[1,0]
18+
19+
precision=true_positive/(true_positive+false_positive)
20+
recall=true_positive/(true_positive+false_negative)
21+
22+
print("Precision Confusion Matrix : ",precision);
23+
print("Recall Confusion Matrix : ",recall);
Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
import nltk
2+
from nltk import word_tokenize, pos_tag
3+
4+
nltk.download("punkt")
5+
nltk.download("averaged_perceptron_tagger")
6+
7+
sentence = "The quick brown fox jumps over the lazy dog."
8+
9+
words = word_tokenize(sentence)
10+
11+
print(pos_tag(words))

‎ICTAcadamy/Week-2/Vectorization.py‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
import pandas as pd
2+
from sklearn.feature_extraction.text import TfidfVectorizer
3+
4+
documents = [
5+
"I am Nithin.",
6+
"K Ramakrishnan Collge of Technology.",
7+
"Fourth Year Student.",
8+
"Consider me as Document Data",
9+
]
10+
11+
a = TfidfVectorizer()
12+
13+
tfidf_matrix = a.fit_transform(documents)
14+
15+
feature_names = a.get_feature_names_out()
16+
17+
out = pd.DataFrame(data=tfidf_matrix.toarray(), columns=feature_names)
18+
19+
print(out)

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /