使用scikit-learn解决文本多分类问题(附python演练)

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

from io import StringIO
col = ['Product', 'Consumer complaint narrative']
df = df[col]
df = df[pd.notnull(df['Consumer complaint narrative'])]
df.columns = ['Product', 'Consumer_complaint_narrative']
df['category_id'] = df['Product'].factorize()[0]
category_id_df = df[['Product', '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', 'Product']].values)
df.head()

Import matplotlib.pyplot as plt
fig = plt.figure(figsize=(8,6))
df.groupby('Product').Consumer_complaint_narrative.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.Consumer_complaint_narrative).toarray()
labels = df.category_id
features.shape
（4569,12633）

from sklearn.feature_selection import chi2
import numpy as np
N = 2
for Product, 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(Product))
  print("  . Most correlated unigrams:n. {}".format('n. '.join(unigrams[-N:])))
  print("  . Most correlated bigrams:n. {}".format('n. '.join(bigrams[-N:])))
 
# ‘Bank account or service’:
 . Most correlated unigrams:
 . bank
 . overdraft
 . Most correlated bigrams:
 . overdraft fees
 . checking account
# ‘Consumer Loan’:
 . Most correlated unigrams:
 . car
 . vehicle
 . Most correlated bigrams:
 . vehicle xxxx
 . toyota financial
# ‘Credit card’:
 . Most correlated unigrams:
 . citi
 . card
 . Most correlated bigrams:
 . annual fee
 . credit card
# ‘Credit reporting’:
 . Most correlated unigrams:
 . experian
 . equifax
 . Most correlated bigrams:
 . trans union
 . credit report
# ‘Debt collection’:
 . Most correlated unigrams:
 . collection
 . debt
 . Most correlated bigrams:
 . collect debt
 . collection agency
# ‘Money transfers’:
 . Most correlated unigrams:
 . wu
 . paypal
 . Most correlated bigrams:
 . western union
 . money transfer
# ‘Mortgage’:
 . Most correlated unigrams:
 . modification
 . mortgage
 . Most correlated bigrams:
 . mortgage company
 . loan modification

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['Consumer_complaint_narrative'], df['Product'], 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)
clf = MultinomialNB().fit(X_train_tfidf, y_train)

print(clf.predict(count_vect.transform(["This company refuses to provide me verification and validation of debt per my right under the FDCPA. I do not believe this debt is mine."])))
[‘Debt collection’]
 
df[df['Consumer_complaint_narrative'] == "This company refuses to provide me verification and validation of debt per my right under the FDCPA. I do not believe this debt is mine."]
 
 
print(clf.predict(count_vect.transform(["I am disputing the inaccurate information the Chex-Systems has on my credit report. I initially submitted a police report on XXXX/XXXX/16 and Chex Systems only deleted the items that I mentioned in the letter and not all the items that were actually listed on the police report. In other words they wanted me to say word for word to them what items were fraudulent. The total disregard of the police report and what accounts that it states that are fraudulent. If they just had paid a little closer attention to the police report I would not been in this position now and they would n't have to research once again. I would like the reported information to be removed : XXXX XXXX XXXX"])))
[‘Credit reporting’]
 
df[df['Consumer_complaint_narrative'] == "I am disputing the inaccurate information the Chex-Systems has on my credit report. I initially submitted a police report on XXXX/XXXX/16 and Chex Systems only deleted the items that I mentioned in the letter and not all the items that were actually listed on the police report. In other words they wanted me to say word for word to them what items were fraudulent. The total disregard of the police report and what accounts that it states that are fraudulent. If they just had paid a little closer attention to the police report I would not been in this position now and they would n't have to research once again. I would like the reported information to be removed : XXXX XXXX XXXX"]
 

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier
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 * len(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_name
LinearSVC: 0.822890
LogisticRegression: 0.792927
MultinomialNB: 0.688519
RandomForestClassifier: 0.443826
Name: accuracy, dtype: float64

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.Product.values, yticklabels=category_id_df.Product.values)
plt.ylabel('Actual')
plt.xlabel('Predicted')
plt.show()

from IPython.display import display
for predicted in category_id_df.category_id:
  for actual in category_id_df.category_id:
    if predicted != actual and conf_mat[actual, predicted] >= 10:
      print("'{}' predicted as '{}' : {} examples.".format(id_to_category[actual], id_to_category[predicted], conf_mat[actual, predicted]))
      display(df.loc[indices_test[(y_test == actual) & (y_pred == predicted)]][['Product', 'Consumer_complaint_narrative']])
      print('')

model.fit(features, labels)
N = 2
for Product, category_id in sorted(category_to_id.items()):
  indices = np.argsort(model.coef_[category_id])
  feature_names = np.array(tfidf.get_feature_names())[indices]
  unigrams = [v for v in reversed(feature_names) if len(v.split(' ')) == 1][:N]
  bigrams = [v for v in reversed(feature_names) if len(v.split(' ')) == 2][:N]
  print("# '{}':".format(Product))
  print("  . Top unigrams:n       . {}".format('n       . '.join(unigrams)))
  print("  . Top bigrams:n       . {}".format('n       . '.join(bigrams)))
 
# ‘Bank account or service’:
 . Top unigrams:
 . bank
 . account
 . Top bigrams:
 . debit card
 . overdraft fees
# ‘Consumer Loan’:
 . Top unigrams:
 . vehicle
 . car
 . Top bigrams:
 . personal loan
 . history xxxx
# ‘Credit card’:
 . Top unigrams:
 . card
 . discover
 . Top bigrams:
 . credit card
 . discover card
# ‘Credit reporting’:
 . Top unigrams:
 . equifax
 . transunion
 . Top bigrams:
 . xxxx account
 . trans union
# ‘Debt collection’:
 . Top unigrams:
 . debt
 . collection
 . Top bigrams:
 . account credit
 . time provided 

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