Python থেকে মেশিন লার্নিং: আপনার প্রথম মডেল

from sklearn.datasets import load_iris

iris = load_iris(as_frame=True)
df = iris.frame                      # একটা pandas DataFrame
print(df.shape)
print(df.head(3).to_string())
print(iris.target_names.tolist())
print(df["target"].value_counts().sort_index().tolist())

(150, 5)
   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  target
0                5.1               3.5                1.4               0.2       0
1                4.9               3.0                1.4               0.2       0
2                4.7               3.2                1.3               0.2       0
['setosa', 'versicolor', 'virginica']
[50, 50, 50]

import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

iris = load_iris(as_frame=True)
df = iris.frame

X = df.drop(columns="target")        # ফিচার: চারটা মাপ
y = df["target"]                     # লেবেল: 0, 1 বা 2

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)
print(X_train.shape, X_test.shape)

model = DecisionTreeClassifier(max_depth=3, random_state=42)
model.fit(X_train, y_train)                    # ট্রেনিং সেট থেকে শেখা

predictions = model.predict(X_test)            # যে ফুল কখনো দেখেনি, তার অনুমান
print(predictions[:10])
print(y_test.to_numpy()[:10])
print(f"accuracy: {accuracy_score(y_test, predictions):.2f}")

new_flower = pd.DataFrame([[5.0, 3.4, 1.5, 0.2]], columns=X.columns)
print(iris.target_names[model.predict(new_flower)[0]])

(120, 4) (30, 4)
[0 2 1 1 0 1 0 0 2 1]
[0 2 1 1 0 1 0 0 2 1]
accuracy: 0.97
setosa

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier

X, y = load_iris(return_X_y=True, as_frame=True)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

for depth in [1, 3, None]:
    model = DecisionTreeClassifier(max_depth=depth, random_state=42).fit(X_train, y_train)
    print(f"max_depth={depth}: train {model.score(X_train, y_train):.2f}, test {model.score(X_test, y_test):.2f}")

max_depth=1: train 0.67, test 0.67
max_depth=3: train 0.98, test 0.97
max_depth=None: train 1.00, test 0.93

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier

X, y = load_iris(return_X_y=True, as_frame=True)
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)

models = {
    "decision tree": DecisionTreeClassifier(max_depth=3, random_state=42),
    "logistic regression": make_pipeline(StandardScaler(), LogisticRegression()),
    "nearest neighbours": make_pipeline(StandardScaler(), KNeighborsClassifier(n_neighbors=5)),
}
for name, model in models.items():
    model.fit(X_train, y_train)
    print(f"{name:20} {model.score(X_test, y_test):.2f}")

decision tree        0.97
logistic regression  0.93
nearest neighbours   0.93

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

reviews = [
    "great sound and battery", "love it, works perfectly", "excellent quality, fast delivery",
    "very happy with this keyboard", "amazing value for money", "good product, would buy again",
    "broke after two days", "terrible support, never again", "stopped charging, very poor",
    "arrived late and damaged", "waste of money", "bad quality, keys stopped working",
]
labels = ["positive"] * 6 + ["negative"] * 6

model = make_pipeline(TfidfVectorizer(), LogisticRegression())
model.fit(reviews, labels)

new_reviews = ["the battery is great", "poor quality, it broke", "fast delivery, happy"]
for text, label in zip(new_reviews, model.predict(new_reviews)):
    print(f"{label:9} <- {text}")

positive  <- the battery is great
negative  <- poor quality, it broke
positive  <- fast delivery, happy

ডেটা  →  পরিষ্কার ও খোঁজাখুঁজি  →  ফিচার (X) আর লেবেল (y)  →  ট্রেন/টেস্ট ভাগ
      →  ট্রেন অংশে fit  →  টেস্ট অংশে মূল্যায়ন  →  উন্নতি  →  নতুন ডেটায় ব্যবহার