teradataml 17.20.0.7__py3-none-any.whl → 20.0.0.1__py3-none-any.whl

teradataml/data/scripts/sklearn/sklearn_model_selection_split.py

@@ -0,0 +1,148 @@
+import pickle
+import math
+import sys
+import numpy as np
+import base64
+
+DELIMITER = '\t'
+
+def get_values_list(values, types):
+    ret_vals = []
+    for i, val in enumerate(values):
+        ret_vals.append(convert_to_type(val, types[i]))
+    return ret_vals
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+
+# Arguments to the Script
+if len(sys.argv) != 9:
+    # 9 arguments command line arguments should be passed to this file.
+    # 1: file to be run
+    # 2. function name
+    # 3. No of feature columns.
+    # 4. No of class labels.
+    # 5. No of group columns.
+    # 6. Comma separated indices of partition columns.
+    # 7. Comma separated types of all the data columns.
+    # 8. Model file prefix to generated model file using partition columns.
+    # 9. Flag to check the system type. True, means Lake, Enterprise otherwise.
+    sys.exit("9 arguments command line arguments should be passed: file to be run,"
+             " function name, no of feature columns, no of class labels, no of group columns,"
+             " comma separated indices of partition columns, comma separated types of all columns,"
+             " model file prefix to generated model file using partition columns and flag to check"
+             " lake or enterprise.")
+
+
+is_lake_system = eval(sys.argv[8])
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+function_name = sys.argv[1]
+n_f_cols = int(sys.argv[2])
+n_c_labels = int(sys.argv[3])
+n_g_cols = int(sys.argv[4])
+data_column_types = splitter(sys.argv[6], delim="--")
+data_partition_column_indices = splitter(sys.argv[5], convert_to="int") # indices are integers.
+model_file_prefix = sys.argv[7]
+
+data_partition_column_types = [data_column_types[idx] for idx in data_partition_column_indices]
+
+model = None
+data_partition_column_values = []
+
+# Data Format (n_features, k_labels, one data_partition_column):
+# feature1, feature2, ..., featuren, label1, label2, ... labelk, data_partition_column1, ..., 
+# data_partition_columnn.
+# labels are optional.
+
+features = []
+labels = []
+groups = []
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            values = line.split(DELIMITER)
+            values = get_values_list(values, data_column_types)
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}" \
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+                with open(model_file_path, "rb") as fp:
+                    model = pickle.loads(fp.read())
+
+                if not model:
+                    sys.exit("Model file is not installed in Vantage.")
+
+            start = 0
+            if n_f_cols > 0:
+                features.append(values[:n_f_cols])
+                start = start + n_f_cols
+            if n_c_labels > 0:
+                labels.append(values[start:(start+n_c_labels)])
+                start = start + n_c_labels
+            if n_g_cols > 0:
+                groups.append(values[start:(start+n_g_cols)])
+
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break
+
+if len(features) == 0:
+    sys.exit(0)
+
+features = np.array(features) if len(features) > 0 else None
+labels = np.array(labels).flatten() if len(labels) > 0 else None
+groups = np.array(groups).flatten() if len(groups) > 0 else None
+
+if function_name == "split":
+    # Printing both train and test data instead of just indices unlike sklearn.
+    # Generator is created based on split_id and type of split (train/test) in client.
+    split_id = 1
+    for train_idx, test_idx in model.split(features, labels, groups):
+        X_train, X_test = features[train_idx], features[test_idx]
+        y_train, y_test = labels[train_idx], labels[test_idx]
+        for X, y in zip(X_train, y_train):
+            print(*(data_partition_column_values + [split_id, "train"] +
+                    ['' if (val is None or (not isinstance(val, str) and (math.isnan(val) or math.isinf(val)))) else val 
+                     for val in X] + [y]
+                    ), sep=DELIMITER)
+        for X, y in zip(X_test, y_test):
+            print(*(data_partition_column_values + [split_id, "test"] +
+                    ['' if (val is None or (not isinstance(val, str) and (math.isnan(val) or math.isinf(val)))) else val 
+                     for val in X] + [y]
+                    ), sep=DELIMITER)
+        split_id += 1
+else:
+    val = getattr(model, function_name)(features, labels, groups)
+    print(*(data_partition_column_values + [val]), sep=DELIMITER)

teradataml/data/scripts/sklearn/sklearn_neighbors.py

@@ -0,0 +1,143 @@
+import pickle
+import math
+import sys
+import numpy as np
+
+# The below import is needed to convert sparse matrix to dense array as sparse matrices are NOT
+# supported in Vantage.
+# This is in scipy 1.6.x. Might vary based on scipy version.
+from scipy.sparse.csr import csr_matrix
+
+
+DELIMITER = '\t'
+
+
+def get_values_list(values, types):
+    ret_vals = []
+    for i, val in enumerate(values):
+        ret_vals.append(convert_to_type(val, types[i]))
+    return ret_vals
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+
+# Arguments to the Script
+if len(sys.argv) < 7:
+    # At least 7 arguments command line arguments should be passed to this file.
+    # 1: file to be run
+    # 2. function name.
+    # 3. No of feature columns.
+    # 4. Comma separated indices of partition columns.
+    # 5. Comma separated types of all the data columns.
+    # 6. Model file prefix to generate model file using partition columns.
+    # 7. Flag to check the system type. True, means Lake, Enterprise otherwise.
+    # 8. OPTIONAL - Arguments in string format like "return_distance True-bool",
+    #    "n_neighbors 3-int", "radius 3.4-float" etc.
+    sys.exit("At least 7 arguments should be passed to this file - file to be run, function name, "\
+             "no of feature columns, comma separated indices of partition columns, comma "\
+             "separated types of all columns, model file prefix to generate model file using "\
+             "partition columns, flag to check lake or enterprise and optional arguments in string format.")
+
+convert_to_int = lambda x: int(x) if x != "None" else None
+
+is_lake_system = eval(sys.argv[6])
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+func_name = sys.argv[1]
+n_f_cols = convert_to_int(sys.argv[2])
+data_column_types = splitter(sys.argv[4], delim="--")
+data_partition_column_indices = splitter(sys.argv[3], convert_to="int") # indices are integers.
+model_file_prefix = sys.argv[5]
+# Extract arguments from string.
+arguments = {}
+for i in range(7, len(sys.argv), 2):
+    value = sys.argv[i + 1].split("-", 1)
+    arguments[sys.argv[i]] = convert_to_type(value[0], value[1])
+
+data_partition_column_types = [data_column_types[idx] for idx in data_partition_column_indices]
+
+model = None
+data_partition_column_values = []
+
+# Data Format:
+# feature1, feature2, ..., featuren, label1, label2, ... labelk, data_partition_column1, ..., 
+# data_partition_columnn.
+# label is optional (it is present when label_exists is not "None")
+
+# `return_distance` is needed as the result is a tuple of two arrays when it is True.
+return_distance = arguments.get("return_distance", True) # Default value is True.
+
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            values = line.split(DELIMITER)
+            values = get_values_list(values, data_column_types)
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}" \
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+                with open(model_file_path, "rb") as fp:
+                    model = pickle.loads(fp.read())
+
+                if not model:
+                    sys.exit("Model file is not installed in Vantage.")
+
+            f_ = values[:n_f_cols]
+            if f_:
+                output = getattr(model, func_name)(np.array([f_]), **arguments)
+            else:
+                output = getattr(model, func_name)(**arguments)
+            result_list = f_
+
+            if func_name in ['kneighbors', 'radius_neighbors']:
+                if return_distance:
+                    result_list += [str(output[0][0].tolist()), str(output[1][0].tolist())]
+                else:
+                    result_list += [str(output[0].tolist())]
+            else:
+                # cases like 'kneighbors_graph', 'radius_neighbors_graph' and other functions.
+                if isinstance(output, csr_matrix):
+                    # 'kneighbors_graph', 'radius_neighbors_graph' return sparse matrix.
+                    output = output.toarray()
+                result_list += [str(output[0].tolist())]
+
+            print(*(data_partition_column_values +
+                    ['' if (val is None or (not isinstance(val, str) and
+                                            (math.isnan(val) or math.isinf(val))))
+                        else val
+                    for val in result_list]), sep=DELIMITER)
+
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break

teradataml/data/scripts/sklearn/sklearn_score.py

@@ -0,0 +1,119 @@
+import pickle
+import math
+import sys
+import numpy as np
+
+DELIMITER = '\t'
+
+
+def get_values_list(values, types):
+    ret_vals = []
+    for i, val in enumerate(values):
+        ret_vals.append(convert_to_type(val, types[i]))
+    return ret_vals
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+# Arguments to the Script
+if len(sys.argv) != 8:
+    # 8 command line arguments should be passed to this file.
+    # 1: file to be run
+    # 2. function name (Eg. score, aic etc)
+    # 3. No of feature columns.
+    # 4. No of class labels.
+    # 5. Comma separated indices of partition columns.
+    # 6. Comma separated types of all the data columns.
+    # 7. Model file prefix to generated model file using partition columns.
+    # 8. Flag to check the system type. True, means Lake, Enterprise otherwise.
+    sys.exit("8 arguments should be passed to this file - file to be run, function name, "\
+             "no of feature columns, no of class labels, comma separated indices "
+             "of partition columns, comma separated types of all columns, model file prefix to "\
+             "generate model file using partition columns and flag to check lake or enterprise.")
+
+is_lake_system = eval(sys.argv[7])
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+func_name = sys.argv[1]
+n_f_cols = int(sys.argv[2])
+n_c_labels = int(sys.argv[3])
+data_column_types = splitter(sys.argv[5], delim="--")
+data_partition_column_indices = splitter(sys.argv[4], convert_to="int") # indices are integers.
+model_file_prefix = sys.argv[6]
+
+data_partition_column_types = [data_column_types[idx] for idx in data_partition_column_indices]
+
+model = None
+
+# Data Format (n_features, k_labels, one data_partition_column):
+# feature1, feature2, ..., featuren, label1, label2, ... labelk, data_partition_column1, ..., 
+# data_partition_columnn.
+# labels are optional.
+
+data_partition_column_values = []
+
+features = []
+labels = []
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            values = line.split(DELIMITER)
+            values = get_values_list(values, data_column_types)
+            features.append(values[:n_f_cols])
+            if n_c_labels > 0:
+                labels.append(values[n_f_cols:(n_f_cols+n_c_labels)])
+
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}" \
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+                with open(model_file_path, "rb") as fp:
+                    model = pickle.loads(fp.read())
+
+                if not model:
+                    sys.exit("Model file is not installed in Vantage.")
+
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break
+
+if len(features) == 0:
+    sys.exit(0)
+
+if labels:
+    val = getattr(model, func_name)(np.array(features), np.array(labels))
+else:
+    val = getattr(model, func_name)(np.array(features))
+
+result_val = ['' if (val is None or (not isinstance(val, str) and (math.isnan(val) or math.isinf(val)))) else val]
+print(*(data_partition_column_values + result_val), sep=DELIMITER)

teradataml/data/scripts/sklearn/sklearn_transform.py

@@ -0,0 +1,171 @@
+import pickle
+import math
+import os
+import sys
+import numpy as np
+
+DELIMITER = '\t'
+
+def get_values_list(values, types):
+    ret_vals = []
+    for i, val in enumerate(values):
+        ret_vals.append(convert_to_type(val, types[i]))
+    return ret_vals
+
+def convert_to_type(val, typee):
+    if typee == 'int':
+        return int(val) if val != "" else np.nan
+    if typee == 'float':
+        if isinstance(val, str):
+            val = val.replace(' ', '')
+        return float(val) if val != "" else np.nan
+    if typee == 'bool':
+        return eval(val) if val != "" else None
+    return str(val) if val != "" else None
+
+def splitter(strr, delim=",", convert_to="str"):
+    """
+    Split the string based on delimiter and convert to the type specified.
+    """
+    if strr == "None":
+        return []
+    return [convert_to_type(i, convert_to) for i in strr.split(delim)]
+
+# Process output returned by sklearn function.
+def get_output_data(trans_values, func_name, model_obj, n_c_labels):
+    # Converting sparse matrix to dense array as sparse matrices are NOT
+    # supported in Vantage.
+    module_name = model_obj.__module__.split("._")[0]
+
+    if type(trans_values).__name__ in ["csr_matrix", "csc_matrix"]:
+        trans_values = trans_values.toarray()
+
+    if module_name == "sklearn.cross_decomposition" and n_c_labels > 0 and func_name == "transform":
+        # For cross_decomposition, output is a tuple of arrays when label columns are provided
+        # along with feature columns for transform function. In this case, concatenate the
+        # arrays and return the combined values.
+        if isinstance(trans_values, tuple):
+            return np.concatenate(trans_values, axis=1).tolist()[0]
+
+    if isinstance(trans_values[0], np.ndarray) \
+            or isinstance(trans_values[0], list) \
+            or isinstance(trans_values[0], tuple):
+        # Here, the value returned by sklearn function is list type.
+        opt_list = list(trans_values[0])
+        if func_name == "inverse_transform" and type(model_obj).__name__ == "MultiLabelBinarizer":
+            # output array "trans_values[0]" may not be of same size. It should be of
+            # maximum size of `model.classes_`
+            # Append None to last elements.
+            if len(opt_list) < len(model_obj.classes_):
+                opt_list += [""] * (len(model_obj.classes_) - len(opt_list))
+        return opt_list
+    return [trans_values[0]]
+
+# Arguments to the Script
+if len(sys.argv) != 8:
+    # 8 arguments command line arguments should be passed to this file.
+    # 1: file to be run
+    # 2. function name (Eg. predict, fit etc)
+    # 3. No of feature columns.
+    # 4. No of class labels.
+    # 5. Comma separated indices of partition columns.
+    # 6. Comma separated types of all the data columns.
+    # 7. Model file prefix to generated model file using partition columns.
+    # 8. Flag to check the system type. True, means Lake, Enterprise otherwise.
+    sys.exit("8 arguments should be passed to this file - file to be run, function name, "\
+             "no of feature columns, no of class labels, comma separated indices of partition "\
+             "columns, comma separated types of all columns, model file prefix to generate model "\
+             "file using partition columns and flag to check lake or enterprise.")
+
+is_lake_system = eval(sys.argv[7])
+if not is_lake_system:
+    db = sys.argv[0].split("/")[1]
+func_name = sys.argv[1]
+n_f_cols = int(sys.argv[2])
+n_c_labels = int(sys.argv[3])
+data_column_types = splitter(sys.argv[5], delim="--")
+data_partition_column_indices = splitter(sys.argv[4], convert_to="int") # indices are integers.
+model_file_prefix = sys.argv[6]
+
+data_partition_column_types = [data_column_types[idx] for idx in data_partition_column_indices]
+
+model = None
+data_partition_column_values = []
+
+# Data Format:
+# feature1, feature2, ..., featuren, label1, label2, ... labelk, data_partition_column1, ..., 
+# data_partition_columnn.
+# label is optional (it is present when label_exists is not "None")
+
+while 1:
+    try:
+        line = input()
+        if line == '':  # Exit if user provides blank line
+            break
+        else:
+            values = line.split(DELIMITER)
+            values = get_values_list(values, data_column_types)
+            if not data_partition_column_values:
+                # Partition column values is same for all rows. Hence, only read once.
+                for i, val in enumerate(data_partition_column_indices):
+                    data_partition_column_values.append(
+                        convert_to_type(values[val], typee=data_partition_column_types[i])
+                        )
+
+                # Prepare the corresponding model file name and extract model.
+                partition_join = "_".join([str(x) for x in data_partition_column_values])
+                # Replace '-' with '_' as '-' because partition_columns can be negative.
+                partition_join = partition_join.replace("-", "_")
+
+                model_file_path = f"{model_file_prefix}_{partition_join}" \
+                    if is_lake_system else \
+                    f"./{db}/{model_file_prefix}_{partition_join}"
+
+                with open(model_file_path, "rb") as fp:
+                    model = pickle.loads(fp.read())
+
+                if not model:
+                    sys.exit("Model file is not installed in Vantage.")
+
+            f_ = values[:n_f_cols]
+            if n_c_labels > 0:
+                # Labels are present in last column.
+                l_ = values[n_f_cols:n_f_cols+n_c_labels]
+                # predict() now takes 'y' also for it to return the labels from script. Skipping 'y'
+                # in function call. Generally, 'y' is passed to return y along with actual output.
+                try:
+                    # cross_composition functions uses Y for labels.
+                    # used 'in' in if constion, as model.__module__ is giving 
+                    # 'sklearn.cross_decomposition._pls'.  
+                    if "cross_decomposition" in model.__module__:
+                        trans_values = getattr(model, func_name)(X=np.array([f_]), Y=np.array([l_]))
+                    else:
+                        trans_values = getattr(model, func_name)(X=np.array([f_]), y=np.array([l_]))
+
+                except TypeError as ex:
+                    # Function which does not accept 'y' like predict_proba() raises error like
+                    # "TypeError: predict_proba() takes 2 positional arguments but 3 were given".
+                    trans_values = getattr(model, func_name)(np.array([f_]))
+            else:
+                # If class labels do not exist in data, don't read labels, read just features.
+                trans_values = getattr(model, func_name)(np.array([f_]))
+
+            result_list = f_
+            if n_c_labels > 0 and func_name in ["predict", "decision_function"]:
+                result_list += l_
+            result_list += get_output_data(trans_values=trans_values, func_name=func_name,
+                                           model_obj=model, n_c_labels=n_c_labels)
+
+            for i, val in enumerate(result_list):
+                if (val is None or (not isinstance(val, str) and (math.isnan(val) or math.isinf(val)))):
+                    result_list[i] = ""
+                # MissingIndicator returns boolean values. Convert them to 0/1.
+                elif val == False:
+                    result_list[i] = 0
+                elif val == True:
+                    result_list[i] = 1
+
+            print(*(data_partition_column_values + result_list), sep=DELIMITER)
+
+    except EOFError:  # Exit if reached EOF or CTRL-D
+        break

teradataml/data/seeds.csv

@@ -1,10 +1,10 @@
-StoreID,SEQ,Sales
-102,2,2.02e+02
-101,1,2.01e+02
-101,2,2.02e+02
-101,3,2.03e+02
-101,4,2.04e+02
-101,5,2.05e+02
-104,4,2.04e+02
-103,3,2.03e+02
-105,5,2.05e+02
+StoreID,SEQ,Sales
+102,2,2.02e+02
+101,1,2.01e+02
+101,2,2.02e+02
+101,3,2.03e+02
+101,4,2.04e+02
+101,5,2.05e+02
+104,4,2.04e+02
+103,3,2.03e+02
+105,5,2.05e+02

teradataml/data/sentenceextractor_example.json

@@ -1,7 +1,7 @@
-{
-  "paragraphs_input": {
-    "paraid": "integer",
-    "paratopic": "varchar(30)",
-    "paratext": "varchar(3000)"
-  }
+{
+  "paragraphs_input": {
+    "paraid": "integer",
+    "paratopic": "varchar(30)",
+    "paratext": "varchar(3000)"
+  }
 }

teradataml/data/sentiment_extract_input.csv

@@ -1,11 +1,11 @@
-"id","product","category","review"
-5,"gps","pos","nice graphs and map route info  .i would not run outside again without this unique gadget  . great job. big display , good backlight , really watertight , training assistant .i use in trail running and  it worked well through out the race"
-9,"television","neg","$3k is way too much money to drop onto a piece of crap .poor customer support . after about 1 and a half years and hardly using the tv , a big yellow pixilated stain appeared. product is very inferior and subject to several lawsuits  . i expressed my dissatifaction with the situation as this is a known issue"
-7,"gps","neg","this machine is all screwed up  . on my way home from a friends house it told me there is no possible route  . i found their website support difficult to navigate . i am is so disapointed and just returned it and now looking for another one"
-6,"gps","neg","most of the complaints i have seen in here are from a lack of rtfm. i have never seen so many mistakes do to what i think has to be none update of data to the system . i wish i could make all the rating stars be empty ."
-3,"camera","pos","this is a nice camera , delivering good quality video images decent photos  ."
-10,"camera","neg","i returned my camera to the vendor as i will not tolerate a sub standard product that is a known issue especially from vendor who will not admt that this needs to be removed from the shelf due to failing parts updated  . due to the constant need for repair , i would never recommend this product  ."
-4,"gps","pos","it is a fine gps . outstanding performance ,  works great . you can even get incredible coordinate accuracy from streets and trips to compare ."
-1,"camera","pos","we primarily bought this camera for high image quality and excellent video capability without paying the price for a dslr  .it has excelled in what we expected of it , and consequently represented excellent value for me  .all my friends want my camera for their vacations  . i would recommend this camera to anybody  .definitely worth the price  .plus , when you buy some accessories , it becomes even more powerful  "
-8,"camera","neg","i hate my camera , and im stuck with it  . this camera sucks so bad , even the dealers on ebay have difficulty selling it. horrible indoors , does not capture fast action, screwy software , no suprise , and screwy audio/video codec that does not work with hardly any app"
-2,"office suite","pos","it is the best office suite i have used to date  . it is launched before office 2010 and it is ages ahead of it already  . the fact that i could comfortable import xls , doc , ppt and modify them , and then export them back to the doc , xls , ppt is terrific . i needed the compatibility  .it is a very intuitive suite and the drag    drop functionality is terrific ."
+"id","product","category","review"
+5,"gps","pos","nice graphs and map route info  .i would not run outside again without this unique gadget  . great job. big display , good backlight , really watertight , training assistant .i use in trail running and  it worked well through out the race"
+9,"television","neg","$3k is way too much money to drop onto a piece of crap .poor customer support . after about 1 and a half years and hardly using the tv , a big yellow pixilated stain appeared. product is very inferior and subject to several lawsuits  . i expressed my dissatifaction with the situation as this is a known issue"
+7,"gps","neg","this machine is all screwed up  . on my way home from a friends house it told me there is no possible route  . i found their website support difficult to navigate . i am is so disapointed and just returned it and now looking for another one"
+6,"gps","neg","most of the complaints i have seen in here are from a lack of rtfm. i have never seen so many mistakes do to what i think has to be none update of data to the system . i wish i could make all the rating stars be empty ."
+3,"camera","pos","this is a nice camera , delivering good quality video images decent photos  ."
+10,"camera","neg","i returned my camera to the vendor as i will not tolerate a sub standard product that is a known issue especially from vendor who will not admt that this needs to be removed from the shelf due to failing parts updated  . due to the constant need for repair , i would never recommend this product  ."
+4,"gps","pos","it is a fine gps . outstanding performance ,  works great . you can even get incredible coordinate accuracy from streets and trips to compare ."
+1,"camera","pos","we primarily bought this camera for high image quality and excellent video capability without paying the price for a dslr  .it has excelled in what we expected of it , and consequently represented excellent value for me  .all my friends want my camera for their vacations  . i would recommend this camera to anybody  .definitely worth the price  .plus , when you buy some accessories , it becomes even more powerful  "
+8,"camera","neg","i hate my camera , and im stuck with it  . this camera sucks so bad , even the dealers on ebay have difficulty selling it. horrible indoors , does not capture fast action, screwy software , no suprise , and screwy audio/video codec that does not work with hardly any app"
+2,"office suite","pos","it is the best office suite i have used to date  . it is launched before office 2010 and it is ages ahead of it already  . the fact that i could comfortable import xls , doc , ppt and modify them , and then export them back to the doc , xls , ppt is terrific . i needed the compatibility  .it is a very intuitive suite and the drag    drop functionality is terrific ."