File size: 4,414 Bytes
c08a470
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
# Title of the document
title: "Pandas Profiling Report"

# Metadata
dataset:
  description: ""
  creator: ""
  author: ""
  copyright_holder: ""
  copyright_year: ""
  url: ""

variables:
  descriptions: {}

# infer dtypes
infer_dtypes: false

# Show the description at each variable (in addition to the overview tab)
show_variable_description: true

# Number of workers (0=multiprocessing.cpu_count())
pool_size: 0

# Show the progress bar
progress_bar: true

# Per variable type description settings
vars:
    num:
        quantiles:
              - 0.05
              - 0.25
              - 0.5
              - 0.75
              - 0.95
        skewness_threshold: 20
        low_categorical_threshold: 5
        # Set to zero to disable
        chi_squared_threshold: 0.0
    cat:
        length: false
        characters: false
        words: false
        cardinality_threshold: 50
        n_obs: 5
        # Set to zero to disable
        chi_squared_threshold: 0.0
        coerce_str_to_date: false
        redact: false
        histogram_largest: 10
        stop_words: []

    bool:
        n_obs: 3
        # string to boolean mapping dict
        mappings:
            t: true
            f: false
            yes: true
            no: false
            y: true
            n: false
            true: true
            false: false
    path:
        active: false
    file:
        active: false
    image:
        active: false
        exif: false
        hash: false
    url:
        active: false
    timeseries:
        active: false
        autocorrelation: 0.7
        lags: [1, 7, 12, 24, 30]
        significance: 0.05
        pacf_acf_lag: 100

# Sort the variables. Possible values: "ascending", "descending" or null (leaves original sorting)
sort: null

# which diagrams to show
missing_diagrams:
    bar: false
    matrix: false
    heatmap: false

correlations:
    pearson:
      calculate: false
      warn_high_correlations: true
      threshold: 0.9
    spearman:
      calculate: false
      warn_high_correlations: false
      threshold: 0.9
    kendall:
      calculate: false
      warn_high_correlations: false
      threshold: 0.9
    phi_k:
      calculate: false
      warn_high_correlations: false
      threshold: 0.9
    cramers:
      calculate: false
      warn_high_correlations: true
      threshold: 0.9
    auto:
       calculate: false
       warn_high_correlations: true
       threshold: 0.9


# Bivariate / Pairwise relations
interactions:
  targets: []
  continuous: false

# For categorical
categorical_maximum_correlation_distinct: 100

report:
  precision: 10

# Plot-specific settings
plot:
    # Image format (svg or png)
    image_format: "svg"
    dpi: 800

    scatter_threshold: 1000

    correlation:
        cmap: 'RdBu'
        bad: '#000000'

    missing:
        cmap: 'RdBu'
        # Force labels when there are > 50 variables
        force_labels: true

    cat_frequency:
        show: true  # if false, the category frequency plot is turned off
        type: 'bar' # options: 'bar', 'pie'
        max_unique: 0
        colors: null # use null for default or give a list of matplotlib recognised strings

    histogram:
        x_axis_labels: true

        # Number of bins (set to 0 to automatically detect the bin size)
        bins: 50

        # Maximum number of bins (when bins=0)
        max_bins: 250

    font_path: null

# The number of observations to show
n_obs_unique: 5
n_extreme_obs: 5
n_freq_table_max: 10

# Use `deep` flag for memory_usage
memory_deep: false

# Configuration related to the duplicates
duplicates:
    head: 0
    key: "# duplicates"

# Configuration related to the samples area
samples:
    head: 0
    tail: 0
    random: 0

# Configuration related to the rejection of variables
reject_variables: true

# When in a Jupyter notebook
notebook:
    iframe:
        height: '800px'
        width: '100%'
        # or 'src'
        attribute: 'srcdoc'

html:
    # Minify the html
    minify_html: true

    # Offline support
    use_local_assets: true

    # If true, single file, else directory with assets
    inline: true

    # Show navbar
    navbar_show: true

    # Assets prefix if inline = true
    assets_prefix: null

    # Styling options for the HTML report
    style:
      theme: null
      logo: ""
      primary_colors:
      - "#377eb8"
      - "#e41a1c"
      - "#4daf4a"

    full_width: false