在本文中，我們將使用 Matplotlib 加入情緒分析結(jié)果的圖形表示。目標(biāo)是可視化多個(gè)句子的情緒分?jǐn)?shù)，並使用長(zhǎng)條圖使用不同的顏色來(lái)區(qū)分正面和負(fù)面情緒。

先決條件

確保您安裝了以下程式庫(kù)：

pip install transformers torch matplotlib

• Transformer：用於處理預(yù)先訓(xùn)練的 NLP 模型。
• torch：用於運(yùn)行模型。
• matplotlib：用於建立情緒分析結(jié)果的圖形表示。

視覺(jué)化 Python 程式碼

這是更新後的 Python 程式碼，它將情緒分析與資料視覺(jué)化整合。

import matplotlib.pyplot as plt
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Load pre-trained model and tokenizer
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize the sentiment-analysis pipeline
classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

# List of 10 sentences for sentiment analysis
sentences = [
    "I love you! I love you! I love you!",
    "I feel so sad today.",
    "This is the best day ever!",
    "I can't stand the rain.",
    "Everything is going so well.",
    "I hate waiting in line.",
    "The weather is nice, but it's cold.",
    "I'm so proud of my achievements.",
    "I am very upset with the decision.",
    "I am feeling optimistic about the future."
]

# Prepare data for the chart
scores = []
colors = []

for sentence in sentences:
    result = classifier(sentence)
    sentiment = result[0]['label']
    score = result[0]['score']
    scores.append(score)

    # Color bars based on sentiment: Positive -> green, Negative -> red
    if sentiment == "POSITIVE":
        colors.append("green")
    else:
        colors.append("red")

# Create a bar chart
plt.figure(figsize=(10, 6))
bars = plt.bar(sentences, scores, color=colors)

# Add labels and title with a line break
plt.xlabel('Sentences')
plt.ylabel('Sentiment Score')
plt.title('Sentiment Analysis of 10 Sentences\n')  # Added newline here
plt.xticks(rotation=45, ha="right")

# Adjust spacing with top margin (to add ceiling space)
plt.subplots_adjust(top=0.85)  # Adjust the top spacing (20px roughly equivalent to 0.1 top margin)

plt.tight_layout()  # Adjusts the rest of the layout

# Display the sentiment score on top of the bars
for bar in bars:
    yval = bar.get_height()
    plt.text(bar.get_x() + bar.get_width() / 2, yval + 0.02, f'{yval:.2f}', ha='center', va='bottom', fontsize=9)

# Show the plot
plt.show()

代碼分解

導(dǎo)入必要的函式庫(kù)：
我們導(dǎo)入 matplotlib.pyplot 來(lái)建立繪圖和轉(zhuǎn)換器來(lái)執(zhí)行情緒分析。

   import matplotlib.pyplot as plt
   from transformers import pipeline
   from transformers import AutoTokenizer, AutoModelForSequenceClassification

載入預(yù)訓(xùn)練模型：
我們載入針對(duì) SST-2 資料集進(jìn)行情緒分析而微調(diào)的 DistilBERT 模型。我們也載入關(guān)聯(lián)的標(biāo)記產(chǎn)生器，將文字轉(zhuǎn)換為模型可讀的標(biāo)記。

   model_name = "distilbert-base-uncased-finetuned-sst-2-english"
   model = AutoModelForSequenceClassification.from_pretrained(model_name)
   tokenizer = AutoTokenizer.from_pretrained(model_name)

初始化情緒分析管道：
分類器管道是為情感分析而設(shè)定的。此管道負(fù)責(zé)對(duì)輸入文字進(jìn)行標(biāo)記、執(zhí)行推理並傳回結(jié)果。

   classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

情緒分析句：
我們建立一個(gè)包含 10 個(gè)句子的清單來(lái)進(jìn)行分析。每句話都是一種獨(dú)特的情感表達(dá)，從非常正面到負(fù)面。

   sentences = [
       "I love you! I love you! I love you!",
       "I feel so sad today.",
       "This is the best day ever!",
       "I can't stand the rain.",
       "Everything is going so well.",
       "I hate waiting in line.",
       "The weather is nice, but it's cold.",
       "I'm so proud of my achievements.",
       "I am very upset with the decision.",
       "I am feeling optimistic about the future."
   ]

處理情緒並準(zhǔn)備資料：
對(duì)於每個(gè)句子，我們對(duì)其情緒進(jìn)行分類並提取分?jǐn)?shù)。根據(jù)情緒標(biāo)籤（正面或負(fù)面），我們?yōu)閳D表中的長(zhǎng)條指定顏色。正面的句子將是綠色的，而負(fù)面的句子將是紅色的。

   scores = []
   colors = []

   for sentence in sentences:
       result = classifier(sentence)
       sentiment = result[0]['label']
       score = result[0]['score']
       scores.append(score)

       if sentiment == "POSITIVE":
           colors.append("green")
       else:
           colors.append("red")

建立長(zhǎng)條圖：
我們使用 matplotlib 建立條形圖。每個(gè)長(zhǎng)條的高度代表一個(gè)句子的情緒分?jǐn)?shù)，顏色區(qū)分正面和負(fù)面情緒。

   plt.figure(figsize=(10, 6))
   bars = plt.bar(sentences, scores, color=colors)

新增標(biāo)籤並調(diào)整版面：
我們透過(guò)旋轉(zhuǎn) x 軸標(biāo)籤以提高可讀性、添加標(biāo)題以及調(diào)整佈局以獲得最佳間距來(lái)自訂繪圖的外觀。

   plt.xlabel('Sentences')
   plt.ylabel('Sentiment Score')
   plt.title('Sentiment Analysis of 10 Sentences\n')  # Added newline here
   plt.xticks(rotation=45, ha="right")
   plt.subplots_adjust(top=0.85)  # Adjust the top spacing
   plt.tight_layout()  # Adjusts the rest of the layout

在條形頂部顯示情緒分?jǐn)?shù)：
我們還在每個(gè)長(zhǎng)條的頂部顯示情緒得分，以使圖表提供更多資訊。

pip install transformers torch matplotlib

顯示圖：
最後，使用 plt.show() 顯示圖表，它渲染繪圖。

import matplotlib.pyplot as plt
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Load pre-trained model and tokenizer
model_name = "distilbert-base-uncased-finetuned-sst-2-english"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Initialize the sentiment-analysis pipeline
classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)

# List of 10 sentences for sentiment analysis
sentences = [
    "I love you! I love you! I love you!",
    "I feel so sad today.",
    "This is the best day ever!",
    "I can't stand the rain.",
    "Everything is going so well.",
    "I hate waiting in line.",
    "The weather is nice, but it's cold.",
    "I'm so proud of my achievements.",
    "I am very upset with the decision.",
    "I am feeling optimistic about the future."
]

# Prepare data for the chart
scores = []
colors = []

for sentence in sentences:
    result = classifier(sentence)
    sentiment = result[0]['label']
    score = result[0]['score']
    scores.append(score)

    # Color bars based on sentiment: Positive -> green, Negative -> red
    if sentiment == "POSITIVE":
        colors.append("green")
    else:
        colors.append("red")

# Create a bar chart
plt.figure(figsize=(10, 6))
bars = plt.bar(sentences, scores, color=colors)

# Add labels and title with a line break
plt.xlabel('Sentences')
plt.ylabel('Sentiment Score')
plt.title('Sentiment Analysis of 10 Sentences\n')  # Added newline here
plt.xticks(rotation=45, ha="right")

# Adjust spacing with top margin (to add ceiling space)
plt.subplots_adjust(top=0.85)  # Adjust the top spacing (20px roughly equivalent to 0.1 top margin)

plt.tight_layout()  # Adjusts the rest of the layout

# Display the sentiment score on top of the bars
for bar in bars:
    yval = bar.get_height()
    plt.text(bar.get_x() + bar.get_width() / 2, yval + 0.02, f'{yval:.2f}', ha='center', va='bottom', fontsize=9)

# Show the plot
plt.show()

樣本輸出

此程式碼的輸出將是一個(gè)顯示 10 個(gè)句子的情緒分?jǐn)?shù)的長(zhǎng)條圖。正面的句子將以綠色條表示，而負(fù)面的句子將顯示為紅色條。情緒分?jǐn)?shù)將顯示在每個(gè)長(zhǎng)條上方，顯示模型的置信水準(zhǔn)。

結(jié)論

透過(guò)將情緒分析與資料視覺(jué)化結(jié)合，我們可以更好地解讀文字資料背後的情緒基調(diào)。本文中的圖形表示可以讓您更清楚地了解情緒分佈，使您可以輕鬆發(fā)現(xiàn)文字中的趨勢(shì)。您可以將此技術(shù)應(yīng)用於各種用例，例如分析產(chǎn)品評(píng)論、社交媒體貼文或客戶回饋。

透過(guò) Hugging Face 的轉(zhuǎn)換器和 matplotlib 的強(qiáng)大組合，可以擴(kuò)展和自訂此工作流程以適應(yīng)各種 NLP 任務(wù)。

以上是使用 Matplotlib 在 Python 中視覺(jué)化情緒分析結(jié)果的詳細(xì)內(nèi)容。更多資訊請(qǐng)關(guān)注PHP中文網(wǎng)其他相關(guān)文章！