AttributeError: module 'pandas' has no attribute 'to_csv'

Question

I took some rows from csv file like this

pd.DataFrame(CV_data.take(5), columns=CV_data.columns) 

and performed some functions on it. now i want to save it in csv again but it is giving error module 'pandas' has no attribute 'to_csv' I am trying to save it like this

pd.to_csv(CV_data, sep='\t', encoding='utf-8') 

here is my full code. how can i save my resulting data in csv or 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') 

Answer 1

to_csv is a method of a DataFrame object, not of the pandas module.

df = pd.DataFrame(CV_data.take(5), columns=CV_data.columns)

# whatever manipulations on df

df.to_csv(...)

You also have a line pd.DataFrame(CV_data.take(5), columns=CV_data.columns) in your code.

This line creates a dataframe and then discards it. Even if you were successfully calling to_csv, none of your changes to CV_data would have been reflected in that dataframe (and therefore in the outputed csv file).

Answer 2

This will do the job!

#Create a DataFrame:    
new_df = pd.DataFrame({'id': [1,2,3,4,5], 'LETTERS': ['A','B','C','D','E'], 'letters': ['a','b','c','d','e']})

#Save it as csv in your folder:    
new_df.to_csv('C:\\Users\\You\\Desktop\\new_df.csv')