我从 csv 文件中取出了一些行，如下所示
pd.DataFrame(CV_data.take(5), columns=CV_data.columns)
并对其执行一些功能。现在我想再次将其保存在 csv 中，但出现错误module 'pandas' has no attribute 'to_csv'我想像这样保存它
pd.to_csv(CV_data, sep='\t', encoding='utf-8')
这是我的完整代码。如何将生成的数据保存为 csv 或 excel？
# Disable warnings, set Matplotlib inline plotting and load Pandas package
import warnings
warnings.filterwarnings('ignore')
%matplotlib inline
import pandas as pd
pd.options.display.mpl_style = 'default'
CV_data = sqlContext.read.load('Downloads/data/churn-bigml-80.csv',
format='com.databricks.spark.csv',
header='true',
inferSchema='true')
final_test_data = sqlContext.read.load('Downloads/data/churn-bigml-20.csv',
format='com.databricks.spark.csv',
header='true',
inferSchema='true')
CV_data.cache()
CV_data.printSchema()
pd.DataFrame(CV_data.take(5), columns=CV_data.columns)
from pyspark.sql.types import DoubleType
from pyspark.sql.functions import UserDefinedFunction
binary_map = {'Yes':1.0, 'No':0.0, True:1.0, False:0.0}
toNum = UserDefinedFunction(lambda k: binary_map[k], DoubleType())
CV_data = CV_data.drop('State').drop('Area code') \
.drop('Total day charge').drop('Total eve charge') \
.drop('Total night charge').drop('Total intl charge') \
.withColumn('Churn', toNum(CV_data['Churn'])) \
.withColumn('International plan', toNum(CV_data['International plan'])) \
.withColumn('Voice mail plan', toNum(CV_data['Voice mail plan'])).cache()
final_test_data = final_test_data.drop('State').drop('Area code') \
.drop('Total day charge').drop('Total eve charge') \
.drop('Total night charge').drop('Total intl charge') \
.withColumn('Churn', toNum(final_test_data['Churn'])) \
.withColumn('International plan', toNum(final_test_data['International plan'])) \
.withColumn('Voice mail plan', toNum(final_test_data['Voice mail plan'])).cache()
pd.DataFrame(CV_data.take(5), columns=CV_data.columns)
from pyspark.mllib.regression import LabeledPoint
from pyspark.mllib.tree import DecisionTree
def labelData(data):
# label: row[end], features: row[0:end-1]
return data.map(lambda row: LabeledPoint(row[-1], row[:-1]))
training_data, testing_data = labelData(CV_data).randomSplit([0.8, 0.2])
model = DecisionTree.trainClassifier(training_data, numClasses=2, maxDepth=2,
categoricalFeaturesInfo={1:2, 2:2},
impurity='gini', maxBins=32)
print (model.toDebugString())
print ('Feature 12:', CV_data.columns[12])
print ('Feature 4: ', CV_data.columns[4] )
from pyspark.mllib.evaluation import MulticlassMetrics
def getPredictionsLabels(model, test_data):
predictions = model.predict(test_data.map(lambda r: r.features))
return predictions.zip(test_data.map(lambda r: r.label))
def printMetrics(predictions_and_labels):
metrics = MulticlassMetrics(predictions_and_labels)
print ('Precision of True ', metrics.precision(1))
print ('Precision of False', metrics.precision(0))
print ('Recall of True ', metrics.recall(1))
print ('Recall of False ', metrics.recall(0))
print ('F-1 Score ', metrics.fMeasure())
print ('Confusion Matrix\n', metrics.confusionMatrix().toArray())
predictions_and_labels = getPredictionsLabels(model, testing_data)
printMetrics(predictions_and_labels)
CV_data.groupby('Churn').count().toPandas()
stratified_CV_data = CV_data.sampleBy('Churn', fractions={0: 388./2278, 1: 1.0}).cache()
stratified_CV_data.groupby('Churn').count().toPandas()
pd.to_csv(CV_data, sep='\t', encoding='utf-8')
