I have these two function and when I run them my kernel dies so freaking quickly. What can I do to prevent it? It happens after appending about 10 files to the dataframe. Unfortunately json files are such big (approx. 150 MB per one, having dozens of them) and I have no idea how to join it together.
import os import pandas as pd from pandas.io.json import json_normalize import json def filtering_nodes(df): id_list = df.index.tolist() print("Dropping rows without 4 nodes and 3 members...") for x in id_list: if len(df['Nodes'][x]) != 4 and len(df['Members'][x]) != 3: df = df.drop(x) print("Converting to csv...") df.to_csv("whole_df.csv", sep='t') return df def merge_JsonFiles(filename): result = list() cnt = 0 df_all = None data_all = None for f1 in filename: print("Appending file: ", f1) with open('../../data' + f1, 'r') as infile: data_all = json.loads(infile.read()) if cnt == 0: df_all = pd.json_normalize(data_all, record_path =['List2D'], max_level =2 ,sep = "-") else: df_all = df_all.append(pd.json_normalize(data_all, record_path =['List2D'], max_level =2 ,sep = "-"), ignore_index = True) cnt += 1 return df_all files = os.listdir('../../data') df_all_test = merge_JsonFiles(files) df_all_test_drop = filtering_nodes(df_all_test)
EDIT: Due to @jlandercy answer, I’ve made this:
def merging_to_csv(): for path in pathlib.Path("../../data/loads_data/Dane/hilti/").glob("*.json"): # Open source file one by one: with path.open() as handler: df = pd.json_normalize(json.load(handler), record_path =['List2D']) # Identify rows to drop (boolean indexing): q = (df["Nodes"] != 4) & (df["Members"] != 3) # Inplace drop (no extra copy in RAM): df.drop(q, inplace=True) # Append data to disk instead of RAM: df.to_csv("output.csv", mode="a", header=False) merging_to_csv()
and I have this type of error:
KeyError Traceback (most recent call last) <ipython-input-55-cf18265ca50e> in <module> ----> 1 merging_to_csv() <ipython-input-54-698c67461b34> in merging_to_csv() 51 q = (df["Nodes"] != 4) & (df["Members"] != 3) 52 # Inplace drop (no extra copy in RAM): ---> 53 df.drop(q, inplace=True) 54 # Append data to disk instead of RAM: 55 df.to_csv("output.csv", mode="a", header=False) /opt/conda/lib/python3.7/site-packages/pandas/util/_decorators.py in wrapper(*args, **kwargs) 309 stacklevel=stacklevel, 310 ) --> 311 return func(*args, **kwargs) 312 313 return wrapper /opt/conda/lib/python3.7/site-packages/pandas/core/frame.py in drop(self, labels, axis, index, columns, level, inplace, errors) 4906 level=level, 4907 inplace=inplace, -> 4908 errors=errors, 4909 ) 4910 /opt/conda/lib/python3.7/site-packages/pandas/core/generic.py in drop(self, labels, axis, index, columns, level, inplace, errors) 4148 for axis, labels in axes.items(): 4149 if labels is not None: -> 4150 obj = obj._drop_axis(labels, axis, level=level, errors=errors) 4151 4152 if inplace: /opt/conda/lib/python3.7/site-packages/pandas/core/generic.py in _drop_axis(self, labels, axis, level, errors) 4183 new_axis = axis.drop(labels, level=level, errors=errors) 4184 else: -> 4185 new_axis = axis.drop(labels, errors=errors) 4186 result = self.reindex(**{axis_name: new_axis}) 4187 /opt/conda/lib/python3.7/site-packages/pandas/core/indexes/base.py in drop(self, labels, errors) 6016 if mask.any(): 6017 if errors != "ignore": -> 6018 raise KeyError(f"{labels[mask]} not found in axis") 6019 indexer = indexer[~mask] 6020 return self.delete(indexer) KeyError: '[ True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True True True True True True True True True True True Truen True] not found in axis'
What’s wrong? I’ll upload two smallest json files here: https://drive.google.com/drive/folders/1xlC-kK6NLGr0isdy1Ln2tzGmel45GtPC?usp=sharing
Advertisement
Answer
You are facing multiple issue in your original approach:
- Multiple copy of dataframe:
df = df.drop(...)
; - Whole information stored in RAM because of
append
; - Unnecessary for loop to filter rows, use boolean indexing instead.
Here is baseline snippet to solve your problem based on data sample you provided:
import json import pathlib import pandas as pd # Iterate source files: for path in pathlib.Path(".").glob("result*.json"): # Open source file one by one: with path.open() as handler: # Normalize JSON model: df = pd.json_normalize(json.load(handler), record_path =['List2D'], max_level=2, sep="-") # Apply len to list fields to identify rows to drop (boolean indexing): q = (df["Nodes"].apply(len) != 4) & (df["Members"].apply(len) != 3) # Filter and append data to disk instead of RAM: df.loc[~q,:].to_csv("output.csv", mode="a", header=False)
It loads file one by one in RAM then append filtered rows to disk not to RAM. Those fixes will drastically reduce RAM usage and should be kept as high as twice the biggest JSON file.