python类read_json()的实例源码

def evaluate(input_path, n_jobs):

    aud, ann = zip(*crema.utils.get_ann_audio(input_path))

    test_idx = set(pd.read_json('index_test.json')['id'])

    # drop anything not in the test set
    ann = [ann_i for ann_i in ann if crema.utils.base(ann_i) in test_idx]
    aud = [aud_i for aud_i in aud if crema.utils.base(aud_i) in test_idx]

    stream = tqdm(zip(ann, aud), desc='Evaluating test set', total=len(ann))

    results = Parallel(n_jobs=n_jobs)(delayed(track_eval)(ann_i, aud_i)
                                      for ann_i, aud_i in stream)
    df = pd.DataFrame.from_dict(dict(results), orient='index')

    print('Results')
    print('-------')
    print(df.describe())

    df.to_json(os.path.join(OUTPUT_PATH, 'test_scores.json'))

def get_stats(self):
        import pandas as pd
        filenames, mode = self._get_files("*.json")
        if mode == "pe":
            df1 = pd.read_json(filenames[0])
            df2 = pd.read_json(filenames[1])
            df  = pd.concat([df1, df2])
            # Should have been sorted !
            df.index = ['R1', 'R2']
        else:
            df = pd.read_json(filenames[0])
            df.index = ['R1']
        df = df[["A", "C", "G", "T", "N", "n_reads", "mean quality", "GC content",
                "average read length", "total bases"]]
        for this in "ACGTN":
            df[this] /= df["total bases"] 
            df[this] *= 100
        return df

def fetch_raw_metadata_frame(self, api_key, page_number):
        if page_number > 1:
            return pd.DataFrame([])

        raw = pd.read_json(
            self._format_metadata_url(
              api_key,
              page_number,
            ),
            orient='index',
        )

        raw = raw.sort_index().reset_index()
        raw.rename(
            columns={'index': 'symbol'},
            inplace=True,
        )

        raw = raw[raw['isFrozen'] == 0]
        return raw

def read_stories_without_tags():
    stories = list()
    current_date = START_DATE
    while current_date <= END_DATE:
        file_in = open("./TopStories/%s.json" % current_date.isoformat(), 'r')
        raw_data = json.loads(str(file_in.read()))
        file_in.close()
        for raw_story in raw_data['stories']:
            story = dict()
            story['top_date'] = current_date.isoformat()
            story['story_id'] = raw_story['story_id']
            story['author'] = raw_story['author']
            story['published_date'] = raw_story['published_date']
            story['recommends'] = raw_story['recommends']
            story['responses'] = raw_story['responses']
            story['tags_count'] = len(raw_story['tags'])
            stories.append(story)
        print(current_date.isoformat())
        current_date = current_date + datetime.timedelta(days=1)
    return pd.read_json(json.dumps(stories))

def read_stories_by_tags():
    tags = list()
    current_date = START_DATE
    while current_date <= END_DATE:
        file_in = open("./TopStories/%s.json" % current_date.isoformat(), 'r')
        raw_data = json.loads(str(file_in.read()))
        file_in.close()
        for raw_story in raw_data['stories']:
            for raw_tag in raw_story['tags']:
                tag = dict()
                tag['top_date'] = current_date.isoformat()
                tag['story_id'] = raw_story['story_id']
                tag['author'] = raw_story['author']
                tag['published_date'] = raw_story['published_date']
                tag['recommends'] = raw_story['recommends']
                tag['responses'] = raw_story['responses']
                tag['name'] = raw_tag['name']
                tag['post_count'] = raw_tag['postCount']
                tag['follower_count'] = raw_tag['metadata']['followerCount']
                tags.append(tag)
        print(current_date.isoformat())
        current_date = current_date + datetime.timedelta(days=1)
    return pd.read_json(json.dumps(tags))

def test_frame_from_json_bad_data(self):
        self.assertRaises(ValueError, read_json, StringIO('{"key":b:a:d}'))

        # too few indices
        json = StringIO('{"columns":["A","B"],'
                        '"index":["2","3"],'
                        '"data":[[1.0,"1"],[2.0,"2"],[null,"3"]]}')
        self.assertRaises(ValueError, read_json, json,
                          orient="split")

        # too many columns
        json = StringIO('{"columns":["A","B","C"],'
                        '"index":["1","2","3"],'
                        '"data":[[1.0,"1"],[2.0,"2"],[null,"3"]]}')
        self.assertRaises(AssertionError, read_json, json,
                          orient="split")

        # bad key
        json = StringIO('{"badkey":["A","B"],'
                        '"index":["2","3"],'
                        '"data":[[1.0,"1"],[2.0,"2"],[null,"3"]]}')
        with tm.assertRaisesRegexp(ValueError, r"unexpected key\(s\): badkey"):
            read_json(json, orient="split")

def test_v12_compat(self):
        df = DataFrame(
            [[1.56808523, 0.65727391, 1.81021139, -0.17251653],
             [-0.2550111, -0.08072427, -0.03202878, -0.17581665],
             [1.51493992, 0.11805825, 1.629455, -1.31506612],
             [-0.02765498, 0.44679743, 0.33192641, -0.27885413],
             [0.05951614, -2.69652057, 1.28163262, 0.34703478]],
            columns=['A', 'B', 'C', 'D'],
            index=pd.date_range('2000-01-03', '2000-01-07'))
        df['date'] = pd.Timestamp('19920106 18:21:32.12')
        df.ix[3, 'date'] = pd.Timestamp('20130101')
        df['modified'] = df['date']
        df.ix[1, 'modified'] = pd.NaT

        v12_json = os.path.join(self.dirpath, 'tsframe_v012.json')
        df_unser = pd.read_json(v12_json)
        assert_frame_equal(df, df_unser)

        df_iso = df.drop(['modified'], axis=1)
        v12_iso_json = os.path.join(self.dirpath, 'tsframe_iso_v012.json')
        df_unser_iso = pd.read_json(v12_iso_json)
        assert_frame_equal(df_iso, df_unser_iso)

def test_date_format_frame(self):
        df = self.tsframe.copy()

        def test_w_date(date, date_unit=None):
            df['date'] = Timestamp(date)
            df.ix[1, 'date'] = pd.NaT
            df.ix[5, 'date'] = pd.NaT
            if date_unit:
                json = df.to_json(date_format='iso', date_unit=date_unit)
            else:
                json = df.to_json(date_format='iso')
            result = read_json(json)
            assert_frame_equal(result, df)

        test_w_date('20130101 20:43:42.123')
        test_w_date('20130101 20:43:42', date_unit='s')
        test_w_date('20130101 20:43:42.123', date_unit='ms')
        test_w_date('20130101 20:43:42.123456', date_unit='us')
        test_w_date('20130101 20:43:42.123456789', date_unit='ns')

        self.assertRaises(ValueError, df.to_json, date_format='iso',
                          date_unit='foo')

def test_date_format_series(self):
        def test_w_date(date, date_unit=None):
            ts = Series(Timestamp(date), index=self.ts.index)
            ts.ix[1] = pd.NaT
            ts.ix[5] = pd.NaT
            if date_unit:
                json = ts.to_json(date_format='iso', date_unit=date_unit)
            else:
                json = ts.to_json(date_format='iso')
            result = read_json(json, typ='series')
            assert_series_equal(result, ts)

        test_w_date('20130101 20:43:42.123')
        test_w_date('20130101 20:43:42', date_unit='s')
        test_w_date('20130101 20:43:42.123', date_unit='ms')
        test_w_date('20130101 20:43:42.123456', date_unit='us')
        test_w_date('20130101 20:43:42.123456789', date_unit='ns')

        ts = Series(Timestamp('20130101 20:43:42.123'), index=self.ts.index)
        self.assertRaises(ValueError, ts.to_json, date_format='iso',
                          date_unit='foo')

def test_date_unit(self):
        df = self.tsframe.copy()
        df['date'] = Timestamp('20130101 20:43:42')
        df.ix[1, 'date'] = Timestamp('19710101 20:43:42')
        df.ix[2, 'date'] = Timestamp('21460101 20:43:42')
        df.ix[4, 'date'] = pd.NaT

        for unit in ('s', 'ms', 'us', 'ns'):
            json = df.to_json(date_format='epoch', date_unit=unit)

            # force date unit
            result = read_json(json, date_unit=unit)
            assert_frame_equal(result, df)

            # detect date unit
            result = read_json(json, date_unit=None)
            assert_frame_equal(result, df)

def test_weird_nested_json(self):
        # this used to core dump the parser
        s = r'''{
        "status": "success",
        "data": {
        "posts": [
            {
            "id": 1,
            "title": "A blog post",
            "body": "Some useful content"
            },
            {
            "id": 2,
            "title": "Another blog post",
            "body": "More content"
            }
           ]
          }
        }'''

        read_json(s)

def test_misc_example(self):

        # parsing unordered input fails
        result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]', numpy=True)
        expected = DataFrame([[1, 2], [1, 2]], columns=['a', 'b'])

        error_msg = """DataFrame\\.index are different

DataFrame\\.index values are different \\(100\\.0 %\\)
\\[left\\]:  Index\\(\\[u?'a', u?'b'\\], dtype='object'\\)
\\[right\\]: RangeIndex\\(start=0, stop=2, step=1\\)"""
        with tm.assertRaisesRegexp(AssertionError, error_msg):
            assert_frame_equal(result, expected, check_index_type=False)

        result = read_json('[{"a": 1, "b": 2}, {"b":2, "a" :1}]')
        expected = DataFrame([[1, 2], [1, 2]], columns=['a', 'b'])
        assert_frame_equal(result, expected)

def _getUserStrategy(self, downloadStrategyInterval=60):
    """??????????????
    downloadStrategyInterval: int default=60 ?
    return: df"""
    k = "SignForWebUser_preLoadTime"
    preLoadTime = myredis.get_obj(k)
    if preLoadTime is None:
        preLoadTime = datetime.datetime(2015, 10, 19, 15, 33, 47, 53000)    #????????
    #????
    if (agl.curTime() - preLoadTime).total_seconds() > downloadStrategyInterval:
        url = "http://stocksign.sinaapp.com/query?cmd=query_strategy"
        result = Http().get(url)
        df_source = pd.read_json(result)
        df_source.columns = ['id', 'user_id', 'title', 'code']
        preLoadTime = agl.curTime()
        myredis.set_obj(k, preLoadTime)
        myredis.set_obj('mysource', df_source)
    else:
        df_source = myredis.get_obj('mysource')
        if df_source is None:
        df_source = pd.DataFrame([])
    return df_source

def read_scraped_jason(filename):
    df = pd.read_json(filename)

    for column in df.columns:
        df[column] = df[column].apply(unlist)
    # gets only first 10 characters of date: year/month/day
    df['date'] = df['date'].apply(lambda x: x[:10])
    df['date'] = pd.to_datetime(df['date'])

    # if any removes duplicate posts
    df = df.drop_duplicates(subset = ['keywords'])
    # sorts dataframe by post date
    df = df.sort_values(by='date')

    df = df.drop('body', 1)
    df = df.drop('title', 1)

    df['keywords'].replace('', np.nan, inplace=True)
    df = df.dropna()

    return df

def extract_features_from_json():
    input_path = '../../data/20_5_from_2008/'
    df_list = []
    for json_file in os.listdir(input_path):
        train_data = pd.read_json(os.path.join(input_path, json_file), orient='columns')
        train_data.dropna(inplace=True)
        train_data.sort_index(ascending=False, inplace=True)
        train_data.index = range(len(train_data))
        if len(train_data) > 0:
            data_norm(train_data)

        values = train_data['real_up_after_240'].tolist()
        codes = train_data['code'].tolist()
        train_data.drop(['datetime', 'code', 'real_up_after_240'], axis=1, inplace=True)
        features = train_data.values.tolist()

        with open('../../data/20_5_from_2008/data', 'a') as f:
            for ix in xrange(len(codes)):
                if np.inf not in features[ix] and -np.inf not in features[ix]:
                    f.write('%s;0 %s;1 %f\n' % (codes[ix][2:], ' '.join([str(x) for x in features[ix]]), values[ix]))

def loadStepsData(dumpDir):
    """
    Load steps data from dumping done using the official Fitbit API.
    Check README file for further info on the scraping process and saved format
    :param dumpDir: the folder where the date has been dumped
    :return: a list of dataframes, one for each day, containing the intraday steps data
    """
    def loadFun(jsonData):
        intradayData = jsonData['activities-steps-intraday']['dataset']
        date = jsonData['activities-steps'][0]['dateTime']
        if not intradayData:
            return None
        df = pd.read_json(json.dumps(intradayData))
        df['datetime'] = pd.to_datetime(date + ' ' + df['time'])
        df.drop('time', inplace=True, axis=1)
        return df

    return _loadData(dumpDir, 'steps', loadFun)

def get_orders_frame(self, state=None, kind='auth'):
        q = self.get_orders(state, kind)
        tj = json.dumps(q['orders'])
        df = pd.read_json(tj, convert_dates=['creation_timestamp', 'expiration_timestamp'])
        df.index = df.creation_timestamp
        return df

def processData(data):
    df = pd.DataFrame.transpose(pd.read_json(json.dumps(data)))
    df = df.dropna(subset = [key for key in df.keys() if "x_" in key])
    df = df[pd.notnull(df['y_observed'])]

    X = df[[key for key in df.keys() if "x_" in key]].values
    y = df["y_observed"].values

    return X, y

# 5th: initial model

def read_json_file_into_pandas_df(self, filename, index_col=False):
        json_string = self.read_json_file(filename=filename)
        return pd.read_json(json_string)

def get_bg_dataframe(id_str):
    """
    Function to convert the json file to a pandas dataframe.
    It takes in the string of the id and looks for the devicestatus.json file.
    All data should be stored such that in the directory where main.py lies,
    there is a directory called "data". Inside this directory,
    there is another directory with just the ID Number. Inside this data folder lies the
    devicestatus.json file, which contains the data. If the file is not in the path given,
    it raises an IOError. The path should look like the following example:

    ./data/12345678/devicestatus.json

    Input:      id_str                          ID number as a string
    Output:     bg_df                           Pandas dataframe of all of the data from ./data/[id_str]/devicestatus.json
    Usage:      bg_df = get_bg_dataframe("12345678")
    """

    try:
        file_location = "./data/" + id_str + "/devicestatus.json"
        bg_df = pd.read_json(file_location) #Opens the data file and reads in the data into a dataFrame
    except:
        raise IOError(file_location + " is not a valid file.")

    print
    print("{} total entries.".format(len(bg_df)))

    return bg_df


#Function to find the indices for the given start and end date strings

def file_search(filename, verbose):
    """Search for filename. Returns dirname of the filename's path, and the full path.

    170107 add cache. If the db is not found, create an empty pandas df 
    and populate this df with append later. If the filename is not in the db
    run g/locate. Then, save the found path to the db (using pandas, via df, to json)"""

    # cache
    if os.path.isfile(JSON_DB):
        df = pd.read_json(JSON_DB, orient='records')
        #filename = 'x.pse'
        pathdf = df[df['fn'] == filename]['path']
        if not pathdf.empty:
            path = pathdf.to_string(index=False)
            logger.info('find file [from the db]:' + filename)
            return os.path.dirname(path), path
    else:
        df = pd.DataFrame()

    # if filename is not found in the db
    logger.info('find file:' + filename)

    if platform.system() == "Linux":
        out = commands.getoutput('locate ' + filename)
    if platform.system() == "Darwin":
        out = commands.getoutput('glocate ' + filename)
    first_hit = out.split('\n')[0]
    logger.info('# of hits ' + str(len(out.split('\n'))) + " " + out.replace('\n',', '))
    if not first_hit:
        logger.info('not found')
    else:
        logger.info('hit ' + first_hit)

    # update cache
    dffile = pd.DataFrame([[filename, first_hit],], columns=['fn', 'path'])
    df = df.append(dffile, ignore_index=True)
    # save to json
    df.to_json(JSON_DB, orient='records')
    ##
    return os.path.dirname(first_hit), first_hit

def get_holiday_json(self):
        """
        ???????
        :return:
        """
        path = os.path.join(pwd, 'holiday.json')
        return pd.read_json(path, typ="series").sort_index()

def pd_json_to_df(self, data_json, sorted_by_key="Date", in_ascending=True):
        import pandas as pd
        new_df  = pd.read_json(data_json).sort_values(by=sorted_by_key, ascending=in_ascending)
        return new_df
    # end of pd_json_to_df

def get_raw(filename):
    with open(filename) as infile:
        raw = infile.read()
        # the next line needs rewriting as soon as the zenodo-dump conforms to 'records'-format
        # [{k:v}, {k:v},...]
        rawfacts = pd.read_json('[%s]' % ','.join(raw.splitlines()), orient='records')
    return rawfacts


### functions for ingesting from CProject



### functions for preprocessing

def load_json(filename):
    '''
    Function:
        - opens json file and store information in a pandas dataframe
        - also prints out aggregated df with counts of picture by countrycode
    Input:
        1. filename/path ex: ./data/filename.json
    Output:
        1. new dataframe containing json info
    '''
    df = pd.read_json(filename, lines=True)
    test = df.groupby(df['countrycode']).count()
    print test.sort(columns='drawing',ascending=False).head(15)
    return df

def read_data(project_path):
    print "Reading data..."
    train = pd.read_json(project_path + "/data/train.json")
    test = pd.read_json(project_path + "/data/test.json")

    print "Train size:", len(train.id)
    print "Test size:", len(test.id)

    return train, test

def read_json_file_into_pandas_df(self, filename):
        return pd.read_json(os.path.join(self.src_dir, filename), dtype=np.int8)

def read_json_file_into_pandas_df(self, filename):
        json_string = self.read_json_file(filename=filename)
        return pd.read_json(json_string, dtype=np.int8)

def apiResults(locationInfo):
    query = ("https://data.seattle.gov/resource/pu5n-trf4.json?$limit={}&$where=within_circle(incident_location,{},{},{})"
        .format(locationInfo['limit'],
                locationInfo['latitude'],
                locationInfo['longitude'],
                locationInfo['radius']))
    return pd.read_json(query)

def fetch_raw_symbol_frame(self,
                               api_key,
                               symbol,
                               calendar,
                               start_date,
                               end_date,
                               frequency):

        # TODO: replace this with direct exchange call
        # The end date and frequency should be used to
        # calculate the number of bars
        if(frequency == 'minute'):
            pc = PoloniexCurator()
            raw = pc.onemin_to_dataframe(symbol, start_date, end_date)

        else:
            raw = pd.read_json(
                self._format_data_url(
                    api_key,
                    symbol,
                    start_date,
                    end_date,
                    frequency,
                ),
                orient='records',
            )
            raw.set_index('date', inplace=True)

        # BcolzDailyBarReader introduces a 1/1000 factor in the way
        # pricing is stored on disk, which we compensate here to get
        # the right pricing amounts
        # ref: data/us_equity_pricing.py
        scale = 1
        raw.loc[:, 'open'] /= scale
        raw.loc[:, 'high'] /= scale
        raw.loc[:, 'low'] /= scale
        raw.loc[:, 'close'] /= scale
        raw.loc[:, 'volume'] *= scale

        return raw