Question

我一直在使用以下代码通过分割训练数据集来查找机器学习算法的准确性。我有一个单独的数据集，名为test.csv，仅包含推文，并希望使用机器学习算法和training500.csv预测情绪。这怎么可能呢？

import pandas as pd
df = pd.read_csv('training500.csv')
df.head()

df = df[pd.notnull(df['Text'])]
df.info()
col = ['Text', 'Sentiment']
df = df[col]
df.columns
df.columns = ['Text', 'Sentiment']
df['category_id'] = df['Sentiment'].factorize()[0]
from io import StringIO
category_id_df = df[['Sentiment',       'category_id']].drop_duplicates().sort_values('category_id')
category_to_id = dict(category_id_df.values)
id_to_category = dict(category_id_df[['category_id',   'Sentiment']].values)
df.head()
import matplotlib.pyplot as plt
fig = plt.figure(figsize=(8,6))
df.groupby('Sentiment').Text.count().plot.bar(ylim=0)
plt.show()
from sklearn.feature_extraction.text import TfidfVectorizer

tfidf = TfidfVectorizer(sublinear_tf=True, min_df=5, norm='l2',      encoding='latin-1', ngram_range=(1, 2), stop_words='english')

features = tfidf.fit_transform(df.Text).toarray()
labels = df.category_id
features.shape

from sklearn.feature_selection import chi2
import numpy as np

N = 2
for Sentiment, category_id in sorted(category_to_id.items()):             features_chi2 = chi2(features, labels == category_id)
  indices = np.argsort(features_chi2[0])
  feature_names = np.array(tfidf.get_feature_names())[indices]
  unigrams = [v for v in feature_names if len(v.split(' ')) == 1]
  bigrams = [v for v in feature_names if len(v.split(' '))) == 2]
  print("# '{}':".format(Sentiment))
  print("  . Most correlated unigrams:\n       . {}".format('\n       . '.join(unigrams[-N:])))
  print("  . Most correlated bigrams:\n       . {}".format('\n       . '.join(bigrams[-N:])))


from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.naive_bayes import MultinomialNB

X_train, X_test, y_train, y_test = train_test_split(df['Text'], df['Sentiment'], random_state = 0)
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(X_train)
tfidf_transformer = TfidfTransformer()
X_train_tfidf = tfidf_transformer.fit_transform(X_train_counts)


from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import MultinomialNB
from sklearn.svm import LinearSVC

from sklearn.model_selection import cross_val_score


models = [
    RandomForestClassifier(n_estimators=200, max_depth=3,     random_state=0),
    LinearSVC(),
    MultinomialNB(),
    LogisticRegression(random_state=0),
]
CV = 5
cv_df = pd.DataFrame(index=range(CV * lenstr((models)))
entries = []
for model in models:
  model_name = model.__class__.__name__
  accuracies = cross_val_score(model, features, labels,  scoring='accuracy', cv=CV)
  for fold_idx, accuracy in enumerate(accuracies):
    entries.append((model_name, fold_idx, accuracy))
cv_df = pd.DataFrame(entries, columns=['model_name', 'fold_idx', 'accuracy'])
import seaborn as sns

sns.boxplot(x='model_name', y='accuracy', data=cv_df)
sns.stripplot(x='model_name', y='accuracy', data=cv_df, 
          size=8, jitter=True, edgecolor="gray", linewidth=2)
plt.show()


cv_df.groupby('model_name').accuracy.mean()

model = LinearSVC()
X_train, X_test, y_train, y_test, indices_train, indices_test =    train_test_split(features, labels, df.index, test_size=0.33, random_state=0)
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
from sklearn.metrics import confusion_matrix
conf_mat = confusion_matrix(y_test, y_pred)
fig, ax = plt.subplots(figsize=(10,10))
sns.heatmap(conf_mat, annot=True, fmt='d',
        xticklabels=category_id_df.Sentiment.values,      yticklabels=category_id_df.Sentiment.values)
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.show()

from sklearn import metrics
print(metrics.classification_report(y_test, y_pred,     target_names=df['Sentiment'].unique()))

使用单独的数据集进行情感分析

0 个答案: